The key to the success of few-shot semantic segmentation(FSS)depends on the efficient use of limited annotated support set to accurately segment novel classes in the query set.Due to the few samples in the support set...The key to the success of few-shot semantic segmentation(FSS)depends on the efficient use of limited annotated support set to accurately segment novel classes in the query set.Due to the few samples in the support set,FSS faces challenges such as intra-class differences,background(BG)mismatches between query and support sets,and ambiguous segmentation between the foreground(FG)and BG in the query set.To address these issues,The paper propose a multi-module network called CAMSNet,which includes four modules:the General Information Module(GIM),the Class Activation Map Aggregation(CAMA)module,the Self-Cross Attention(SCA)Block,and the Feature Fusion Module(FFM).In CAMSNet,The GIM employs an improved triplet loss,which concatenates word embedding vectors and support prototypes as anchors,and uses local support features of FG and BG as positive and negative samples to help solve the problem of intra-class differences.Then for the first time,the Class Activation Map(CAM)from the Weakly Supervised Semantic Segmentation(WSSS)is applied to FSS within the CAMA module.This method replaces the traditional use of cosine similarity to locate query information.Subsequently,the SCA Block processes the support and query features aggregated by the CAMA module,significantly enhancing the understanding of input information,leading to more accurate predictions and effectively addressing BG mismatch and ambiguous FG-BG segmentation.Finally,The FFM combines general class information with the enhanced query information to achieve accurate segmentation of the query image.Extensive Experiments on PASCAL and COCO demonstrate that-5i-20ithe CAMSNet yields superior performance and set a state-of-the-art.展开更多
The Internet of Vehicles (IoV) has become an important direction in the field of intelligent transportation, in which vehicle positioning is a crucial part. SLAM (Simultaneous Localization and Mapping) technology play...The Internet of Vehicles (IoV) has become an important direction in the field of intelligent transportation, in which vehicle positioning is a crucial part. SLAM (Simultaneous Localization and Mapping) technology plays a crucial role in vehicle localization and navigation. Traditional Simultaneous Localization and Mapping (SLAM) systems are designed for use in static environments, and they can result in poor performance in terms of accuracy and robustness when used in dynamic environments where objects are in constant movement. To address this issue, a new real-time visual SLAM system called MG-SLAM has been developed. Based on ORB-SLAM2, MG-SLAM incorporates a dynamic target detection process that enables the detection of both known and unknown moving objects. In this process, a separate semantic segmentation thread is required to segment dynamic target instances, and the Mask R-CNN algorithm is applied on the Graphics Processing Unit (GPU) to accelerate segmentation. To reduce computational cost, only key frames are segmented to identify known dynamic objects. Additionally, a multi-view geometry method is adopted to detect unknown moving objects. The results demonstrate that MG-SLAM achieves higher precision, with an improvement from 0.2730 m to 0.0135 m in precision. Moreover, the processing time required by MG-SLAM is significantly reduced compared to other dynamic scene SLAM algorithms, which illustrates its efficacy in locating objects in dynamic scenes.展开更多
Lower back pain is one of the most common medical problems in the world and it is experienced by a huge percentage of people everywhere.Due to its ability to produce a detailed view of the soft tissues,including the s...Lower back pain is one of the most common medical problems in the world and it is experienced by a huge percentage of people everywhere.Due to its ability to produce a detailed view of the soft tissues,including the spinal cord,nerves,intervertebral discs,and vertebrae,Magnetic Resonance Imaging is thought to be the most effective method for imaging the spine.The semantic segmentation of vertebrae plays a major role in the diagnostic process of lumbar diseases.It is difficult to semantically partition the vertebrae in Magnetic Resonance Images from the surrounding variety of tissues,including muscles,ligaments,and intervertebral discs.U-Net is a powerful deep-learning architecture to handle the challenges of medical image analysis tasks and achieves high segmentation accuracy.This work proposes a modified U-Net architecture namely MU-Net,consisting of the Meijering convolutional layer that incorporates the Meijering filter to perform the semantic segmentation of lumbar vertebrae L1 to L5 and sacral vertebra S1.Pseudo-colour mask images were generated and used as ground truth for training the model.The work has been carried out on 1312 images expanded from T1-weighted mid-sagittal MRI images of 515 patients in the Lumbar Spine MRI Dataset publicly available from Mendeley Data.The proposed MU-Net model for the semantic segmentation of the lumbar vertebrae gives better performance with 98.79%of pixel accuracy(PA),98.66%of dice similarity coefficient(DSC),97.36%of Jaccard coefficient,and 92.55%mean Intersection over Union(mean IoU)metrics using the mentioned dataset.展开更多
Automatic segmentation and recognition of content and element information in color geological map are of great significance for researchers to analyze the distribution of mineral resources and predict disaster informa...Automatic segmentation and recognition of content and element information in color geological map are of great significance for researchers to analyze the distribution of mineral resources and predict disaster information.This article focuses on color planar raster geological map(geological maps include planar geological maps,columnar maps,and profiles).While existing deep learning approaches are often used to segment general images,their performance is limited due to complex elements,diverse regional features,and complicated backgrounds for color geological map in the domain of geoscience.To address the issue,a color geological map segmentation model is proposed that combines the Felz clustering algorithm and an improved SE-UNet deep learning network(named GeoMSeg).Firstly,a symmetrical encoder-decoder structure backbone network based on UNet is constructed,and the channel attention mechanism SENet has been incorporated to augment the network’s capacity for feature representation,enabling the model to purposefully extract map information.The SE-UNet network is employed for feature extraction from the geological map and obtain coarse segmentation results.Secondly,the Felz clustering algorithm is used for super pixel pre-segmentation of geological maps.The coarse segmentation results are refined and modified based on the super pixel pre-segmentation results to obtain the final segmentation results.This study applies GeoMSeg to the constructed dataset,and the experimental results show that the algorithm proposed in this paper has superior performance compared to other mainstream map segmentation models,with an accuracy of 91.89%and a MIoU of 71.91%.展开更多
The convolutional neural network(CNN)method based on DeepLabv3+has some problems in the semantic segmentation task of high-resolution remote sensing images,such as fixed receiving field size of feature extraction,lack...The convolutional neural network(CNN)method based on DeepLabv3+has some problems in the semantic segmentation task of high-resolution remote sensing images,such as fixed receiving field size of feature extraction,lack of semantic information,high decoder magnification,and insufficient detail retention ability.A hierarchical feature fusion network(HFFNet)was proposed.Firstly,a combination of transformer and CNN architectures was employed for feature extraction from images of varying resolutions.The extracted features were processed independently.Subsequently,the features from the transformer and CNN were fused under the guidance of features from different sources.This fusion process assisted in restoring information more comprehensively during the decoding stage.Furthermore,a spatial channel attention module was designed in the final stage of decoding to refine features and reduce the semantic gap between shallow CNN features and deep decoder features.The experimental results showed that HFFNet had superior performance on UAVid,LoveDA,Potsdam,and Vaihingen datasets,and its cross-linking index was better than DeepLabv3+and other competing methods,showing strong generalization ability.展开更多
Semantic segmentation plays a foundational role in biomedical image analysis, providing precise information about cellular, tissue, and organ structures in both biological and medical imaging modalities. Traditional a...Semantic segmentation plays a foundational role in biomedical image analysis, providing precise information about cellular, tissue, and organ structures in both biological and medical imaging modalities. Traditional approaches often fail in the face of challenges such as low contrast, morphological variability, and densely packed structures. Recent advancements in deep learning have transformed segmentation capabilities through the integration of fine-scale detail preservation, coarse-scale contextual modeling, and multi-scale feature fusion. This work provides a comprehensive analysis of state-of-the-art deep learning models, including U-Net variants, attention-based frameworks, and Transformer-integrated networks, highlighting innovations that improve accuracy, generalizability, and computational efficiency. Key architectural components such as convolution operations, shallow and deep blocks, skip connections, and hybrid encoders are examined for their roles in enhancing spatial representation and semantic consistency. We further discuss the importance of hierarchical and instance-aware segmentation and annotation in interpreting complex biological scenes and multiplexed medical images. By bridging methodological developments with diverse application domains, this paper outlines current trends and future directions for semantic segmentation, emphasizing its critical role in facilitating annotation, diagnosis, and discovery in biomedical research.展开更多
Semantic segmentation of remote sensing images is a critical research area in the field of remote sensing.Despite the success of Convolutional Neural Networks(CNNs),they often fail to capture inter-layer feature relat...Semantic segmentation of remote sensing images is a critical research area in the field of remote sensing.Despite the success of Convolutional Neural Networks(CNNs),they often fail to capture inter-layer feature relationships and fully leverage contextual information,leading to the loss of important details.Additionally,due to significant intraclass variation and small inter-class differences in remote sensing images,CNNs may experience class confusion.To address these issues,we propose a novel Category-Guided Feature Collaborative Learning Network(CG-FCLNet),which enables fine-grained feature extraction and adaptive fusion.Specifically,we design a Feature Collaborative Learning Module(FCLM)to facilitate the tight interaction of multi-scale features.We also introduce a Scale-Aware Fusion Module(SAFM),which iteratively fuses features from different layers using a spatial attention mechanism,enabling deeper feature fusion.Furthermore,we design a Category-Guided Module(CGM)to extract category-aware information that guides feature fusion,ensuring that the fused featuresmore accurately reflect the semantic information of each category,thereby improving detailed segmentation.The experimental results show that CG-FCLNet achieves a Mean Intersection over Union(mIoU)of 83.46%,an mF1 of 90.87%,and an Overall Accuracy(OA)of 91.34% on the Vaihingen dataset.On the Potsdam dataset,it achieves a mIoU of 86.54%,an mF1 of 92.65%,and an OA of 91.29%.These results highlight the superior performance of CG-FCLNet compared to existing state-of-the-art methods.展开更多
Due to the necessity for lightweight and efficient network models, deploying semantic segmentation models on mobile robots (MRs) is a formidable task. The fundamental limitation of the problem lies in the training per...Due to the necessity for lightweight and efficient network models, deploying semantic segmentation models on mobile robots (MRs) is a formidable task. The fundamental limitation of the problem lies in the training performance, the ability to effectively exploit the dataset, and the ability to adapt to complex environments when deploying the model. By utilizing the knowledge distillation techniques, the article strives to overcome the above challenges with the inheritance of the advantages of both the teacher model and the student model. More precisely, the ResNet152-PSP-Net model’s characteristics are utilized to train the ResNet18-PSP-Net model. Pyramid pooling blocks are utilized to decode multi-scale feature maps, creating a complete semantic map inference. The student model not only preserves the strong segmentation performance from the teacher model but also improves the inference speed of the prediction results. The proposed method exhibits a clear advantage over conventional convolutional neural network (CNN) models, as evident from the conducted experiments. Furthermore, the proposed model also shows remarkable improvement in processing speed when compared with light-weight models such as MobileNetV2 and EfficientNet based on latency and throughput parameters. The proposed KD-SegNet model obtains an accuracy of 96.3% and a mIoU (mean Intersection over Union) of 77%, outperforming the performance of existing models by more than 15% on the same training dataset. The suggested method has an average training time that is only 0.51 times less than same field models, while still achieving comparable segmentation performance. Hence, the semantic segmentation frames are collected, forming the motion trajectory for the system in the environment. Overall, this architecture shows great promise for the development of knowledge-based systems for MR’s navigation.展开更多
Accurate segmentation of camouflage objects in aerial imagery is vital for improving the efficiency of UAV-based reconnaissance and rescue missions.However,camouflage object segmentation is increasingly challenging du...Accurate segmentation of camouflage objects in aerial imagery is vital for improving the efficiency of UAV-based reconnaissance and rescue missions.However,camouflage object segmentation is increasingly challenging due to advances in both camouflage materials and biological mimicry.Although multispectral-RGB based technology shows promise,conventional dual-aperture multispectral-RGB imaging systems are constrained by imprecise and time-consuming registration and fusion across different modalities,limiting their performance.Here,we propose the Reconstructed Multispectral-RGB Fusion Network(RMRF-Net),which reconstructs RGB images into multispectral ones,enabling efficient multimodal segmentation using only an RGB camera.Specifically,RMRF-Net employs a divergentsimilarity feature correction strategy to minimize reconstruction errors and includes an efficient boundary-aware decoder to enhance object contours.Notably,we establish the first real-world aerial multispectral-RGB semantic segmentation of camouflage objects dataset,including 11 object categories.Experimental results demonstrate that RMRF-Net outperforms existing methods,achieving 17.38 FPS on the NVIDIA Jetson AGX Orin,with only a 0.96%drop in mIoU compared to the RTX 3090,showing its practical applicability in multimodal remote sensing.展开更多
Real-time semantic segmentation tasks place stringent demands on network inference speed,often requiring a reduction in network depth to decrease computational load.However,shallow networks tend to exhibit degradation...Real-time semantic segmentation tasks place stringent demands on network inference speed,often requiring a reduction in network depth to decrease computational load.However,shallow networks tend to exhibit degradation in feature extraction completeness and inference accuracy.Therefore,balancing high performance with real-time requirements has become a critical issue in the study of real-time semantic segmentation.To address these challenges,this paper proposes a lightweight bilateral dual-residual network.By introducing a novel residual structure combined with feature extraction and fusion modules,the proposed network significantly enhances representational capacity while reducing computational costs.Specifically,an improved compound residual structure is designed to optimize the efficiency of information propagation and feature extraction.Furthermore,the proposed feature extraction and fusion module enables the network to better capture multi-scale information in images,improving the ability to detect both detailed and global semantic features.Experimental results on the publicly available Cityscapes dataset demonstrate that the proposed lightweight dual-branch network achieves outstanding performance while maintaining low computational complexity.In particular,the network achieved a mean Intersection over Union(mIoU)of 78.4%on the Cityscapes validation set,surpassing many existing semantic segmentation models.Additionally,in terms of inference speed,the network reached 74.5 frames per second when tested on an NVIDIA GeForce RTX 3090 GPU,significantly improving real-time performance.展开更多
Indoor visual localization relies heavily on image retrieval to ascertain location information.However,the widespread presence and high consistency of floor patterns across different images of-ten lead to the extracti...Indoor visual localization relies heavily on image retrieval to ascertain location information.However,the widespread presence and high consistency of floor patterns across different images of-ten lead to the extraction of numerous repetitive features,thereby reducing the accuracy of image retrieval.This article proposes an indoor visual localization method based on semantic segmentation and adaptive weight fusion to address the issue of ground texture interference with retrieval results.During the positioning process,an indoor semantic segmentation model is established.Semantic segmentation technology is applied to accurately delineate the ground portion of the images.Fea-ture extraction is performed on both the original database and the ground-segmented database.The vector of locally aggregated descriptors(VLAD)algorithm is then used to convert image features into a fixed-length feature representation,which improves the efficiency of image retrieval.Simul-taneously,a method for adaptive weight optimization in similarity calculation is proposed,using a-daptive weights to compute similarity for different regional features,thereby improving the accuracy of image retrieval.The experimental results indicate that this method significantly reduces ground interference and effectively utilizes ground information,thereby improving the accuracy of image retrieval.展开更多
Since the introduction of vision Transformers into the computer vision field,many vision tasks such as semantic segmentation tasks,have undergone radical changes.Although Transformer enhances the correlation of each l...Since the introduction of vision Transformers into the computer vision field,many vision tasks such as semantic segmentation tasks,have undergone radical changes.Although Transformer enhances the correlation of each local feature of an image object in the hidden space through the attention mechanism,it is difficult for a segmentation head to accomplish the mask prediction for dense embedding of multi-category and multi-local features.We present patch prototype vision Transformer(PPFormer),a Transformer architecture for semantic segmentation based on knowledge-embedded patch prototypes.1)The hierarchical Transformer encoder can generate multi-scale and multi-layered patch features including seamless patch projection to obtain information of multiscale patches,and feature-clustered self-attention to enhance the interplay of multi-layered visual information with implicit position encodes.2)PPFormer utilizes a non-parametric prototype decoder to extract region observations which represent significant parts of the objects by unlearnable patch prototypes and then calculate similarity between patch prototypes and pixel embeddings.The proposed contrasting patch prototype alignment module,which uses new patch prototypes to update prototype bank,effectively maintains class boundaries for prototypes.For different application scenarios,we have launched PPFormer-S,PPFormer-M and PPFormer-L by expanding the scale.Experimental results demonstrate that PPFormer can outperform fully convolutional networks(FCN)-and attention-based semantic segmentation models on the PASCAL VOC 2012,ADE20k,and Cityscapes datasets.展开更多
Semantic segmentation has made significant breakthroughs in various application fields,but achieving both accurate and efficient segmentation with limited computational resources remains a major challenge.To this end,...Semantic segmentation has made significant breakthroughs in various application fields,but achieving both accurate and efficient segmentation with limited computational resources remains a major challenge.To this end,we propose CGMISeg,an efficient semantic segmentation architecture based on a context-guided multi-scale interaction strategy,aiming to significantly reduce computational overhead while maintaining segmentation accuracy.CGMISeg consists of three core components:context-aware attention modulation,feature reconstruction,and crossinformation fusion.Context-aware attention modulation is carefully designed to capture key contextual information through channel and spatial attention mechanisms.The feature reconstruction module reconstructs contextual information from different scales,modeling key rectangular areas by capturing critical contextual information in both horizontal and vertical directions,thereby enhancing the focus on foreground features.The cross-information fusion module aims to fuse the reconstructed high-level features with the original low-level features during upsampling,promoting multi-scale interaction and enhancing the model’s ability to handle objects at different scales.We extensively evaluated CGMISeg on ADE20K,Cityscapes,and COCO-Stuff,three widely used datasets benchmarks,and the experimental results show that CGMISeg exhibits significant advantages in segmentation performance,computational efficiency,and inference speed,clearly outperforming several mainstream methods,including SegFormer,Feedformer,and SegNext.Specifically,CGMISeg achieves 42.9%mIoU(Mean Intersection over Union)and 15.7 FPS(Frames Per Second)on the ADE20K dataset with 3.8 GFLOPs(Giga Floating-point Operations Per Second),outperforming Feedformer and SegNeXt by 3.7%and 1.8%in mIoU,respectively,while also offering reduced computational complexity and faster inference.CGMISeg strikes an excellent balance between accuracy and efficiency,significantly enhancing both computational and inference performance while maintaining high precision,showcasing exceptional practical value and strong potential for widespread applications.展开更多
Semantic segmentation in street scenes is a crucial technology for autonomous driving to analyze the surrounding environment.In street scenes,issues such as high image resolution caused by a large viewpoints and diffe...Semantic segmentation in street scenes is a crucial technology for autonomous driving to analyze the surrounding environment.In street scenes,issues such as high image resolution caused by a large viewpoints and differences in object scales lead to a decline in real-time performance and difficulties in multi-scale feature extraction.To address this,we propose a bilateral-branch real-time semantic segmentationmethod based on semantic information distillation(BSDNet)for street scene images.The BSDNet consists of a Feature Conversion Convolutional Block(FCB),a Semantic Information Distillation Module(SIDM),and a Deep Aggregation Atrous Convolution Pyramid Pooling(DASP).FCB reduces the semantic gap between the backbone and the semantic branch.SIDM extracts high-quality semantic information fromthe Transformer branch to reduce computational costs.DASP aggregates information lost in atrous convolutions,effectively capturingmulti-scale objects.Extensive experiments conducted on Cityscapes,CamVid,and ADE20K,achieving an accuracy of 81.7% Mean Intersection over Union(mIoU)at 70.6 Frames Per Second(FPS)on Cityscapes,demonstrate that our method achieves a better balance between accuracy and inference speed.展开更多
Neuronal soma segmentation plays a crucial role in neuroscience applications.However,the fine structure,such as boundaries,small-volume neuronal somata and fibers,are commonly present in cell images,which pose a chall...Neuronal soma segmentation plays a crucial role in neuroscience applications.However,the fine structure,such as boundaries,small-volume neuronal somata and fibers,are commonly present in cell images,which pose a challenge for accurate segmentation.In this paper,we propose a 3D semantic segmentation network for neuronal soma segmentation to address this issue.Using an encoding-decoding structure,we introduce a Multi-Scale feature extraction and Adaptive Weighting fusion module(MSAW)after each encoding block.The MSAW module can not only emphasize the fine structures via an upsampling strategy,but also provide pixel-wise weights to measure the importance of the multi-scale features.Additionally,a dynamic convolution instead of normal convolution is employed to better adapt the network to input data with different distributions.The proposed MSAW-based semantic segmentation network(MSAW-Net)was evaluated on three neuronal soma images from mouse brain and one neuronal soma image from macaque brain,demonstrating the efficiency of the proposed method.It achieved an F1 score of 91.8%on Fezf2-2A-CreER dataset,97.1%on LSL-H2B-GFP dataset,82.8%on Thy1-EGFP-Mline dataset,and 86.9%on macaque dataset,achieving improvements over the 3D U-Net model by 3.1%,3.3%,3.9%,and 2.3%,respectively.展开更多
The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods.End-to-end model designs have gaine...The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods.End-to-end model designs have gained significant attention for improving training efficiency.Most current algorithms rely on Convolutional Neural Networks(CNNs)for feature extraction.Although CNNs are proficient at capturing local features,they often struggle with global context,leading to incomplete and false Class Activation Mapping(CAM).To address these limitations,this work proposes a Contextual Prototype-Based End-to-End Weakly Supervised Semantic Segmentation(CPEWS)model,which improves feature extraction by utilizing the Vision Transformer(ViT).By incorporating its intermediate feature layers to preserve semantic information,this work introduces the Intermediate Supervised Module(ISM)to supervise the final layer’s output,reducing boundary ambiguity and mitigating issues related to incomplete activation.Additionally,the Contextual Prototype Module(CPM)generates class-specific prototypes,while the proposed Prototype Discrimination Loss and Superclass Suppression Loss guide the network’s training,(LPDL)(LSSL)effectively addressing false activation without the need for extra supervision.The CPEWS model proposed in this paper achieves state-of-the-art performance in end-to-end weakly supervised semantic segmentation without additional supervision.The validation set and test set Mean Intersection over Union(MIoU)of PASCAL VOC 2012 dataset achieved 69.8%and 72.6%,respectively.Compared with ToCo(pre trained weight ImageNet-1k),MIoU on the test set is 2.1%higher.In addition,MIoU reached 41.4%on the validation set of the MS COCO 2014 dataset.展开更多
In recent years,video coding has been widely applied in the field of video image processing to remove redundant information and improve data transmission efficiency.However,during the video coding process,irrelevant o...In recent years,video coding has been widely applied in the field of video image processing to remove redundant information and improve data transmission efficiency.However,during the video coding process,irrelevant objects such as background elements are often encoded due to environmental disturbances,resulting in the wastage of computational resources.Existing research on video coding efficiency optimization primarily focuses on optimizing encoding units during intra-frame or inter frame prediction after the generation of coding units,neglecting the optimization of video images before coding unit generation.To address this challenge,This work proposes an image semantic segmentation compression algorithm based on macroblock encoding,called image semantic segmentation compression algorithm based on macroblock encoding(ISSC-ME),which consists of three modules.(1)The semantic label generation module generates interesting object labels using a grid-based approach to reduce redundant coding of consecutive frames.(2)The image segmentation network module generates a semantic segmentation image using U-Net.(3)The macroblock coding module,is a block segmentation-based video encoding and decoding algorithm used to compress images and improve video transmission efficiency.Experimental results show that the proposed image semantic segmentation optimization algorithm can reduce the computational costs,and improve the overall accuracy by 1.00%and the mean intersection over union(IoU)by 1.20%.In addition,the proposed compression algorithm utilizes macroblock fusion,resulting in the image compression rate achieving 80.64%.It has been proven that the proposed algorithm greatly reduces data storage and transmission,and enables fast image compression processing at the millisecond level.展开更多
Semantic segmentation of novel object categories with limited labeled data remains a challenging problem in computer vision.Few-shot segmentation methods aim to address this problem by recognizing objects from specifi...Semantic segmentation of novel object categories with limited labeled data remains a challenging problem in computer vision.Few-shot segmentation methods aim to address this problem by recognizing objects from specific target classes with a few provided examples.Previous approaches for few-shot semantic segmentation typically represent target classes using class prototypes.These prototypes are matched with the features of the query set to get segmentation results.However,class prototypes are usually obtained by applying global average pooling on masked support images.Global pooling discards much structural information,which may reduce the accuracy of model predictions.To address this issue,we propose a Category-Guided Frequency Modulation(CGFM)method.CGFM is designed to learn category-specific information in the frequency space and leverage it to provide a twostage guidance for the segmentation process.First,to self-adaptively activate class-relevant frequency bands while suppressing irrelevant ones,we leverage the Dual-Perception Gaussian Band Pre-activation(DPGBP)module to generate Gaussian filters using class embedding vectors.Second,to further enhance category-relevant frequency components in activated bands,we design a Support-Guided Category Response Enhancement(SGCRE)module to effectively introduce support frequency components into the modulation of query frequency features.Experiments on the PASCAL-5^(i) and COCO-20^(i) datasets demonstrate the promising performance of our model.展开更多
Well logging curves serve as indicators of strata attribute changes and are frequently utilized for stratigraphic analysis and comparison.Deep learning,known for its robust feature extraction capabilities,has seen con...Well logging curves serve as indicators of strata attribute changes and are frequently utilized for stratigraphic analysis and comparison.Deep learning,known for its robust feature extraction capabilities,has seen continuous adoption by scholars in the realm of well logging stratigraphic correlation tasks.Nonetheless,current deep learning algorithms often struggle to accurately capture feature changes occurring at layer boundaries within the curves.Moreover,when faced with data imbalance issues,neural networks encounter challenges in accurately modeling the one-hot encoded curve stratification positions,resulting in significant deviations between predicted and actual stratification positions.Addressing these challenges,this study proposes a novel well logging curve stratigraphic comparison algorithm based on uniformly distributed soft labels.In the training phase,a label smoothing loss function is introduced to comprehensively account for the substantial loss stemming from data imbalance and to consider the similarity between diff erent layer data.Concurrently,spatial attention and channel attention mechanisms are incorporated into the shallow and deep encoder stages of U²-Net,respectively,to better focus on changes in stratification positions.During the prediction phase,an optimized confidence threshold algorithm is proposed to constrain stratification results and solve the problem of reduced prediction accuracy because of occasional layer repetition.The proposed method is applied to real-world well logging data in oil fields.Quantitative evaluation results demonstrate that within error ranges of 1,2,and 3 m,the accuracy of well logging curve stratigraphic division reaches 87.27%,92.68%,and 95.08%,respectively,thus validating the eff ectiveness of the algorithm presented in this paper.展开更多
With the rapid development of artificial intelligence and the widespread use of the Internet of Things, semantic communication, as an emerging communication paradigm, has been attracting great interest. Taking image t...With the rapid development of artificial intelligence and the widespread use of the Internet of Things, semantic communication, as an emerging communication paradigm, has been attracting great interest. Taking image transmission as an example, from the semantic communication's view, not all pixels in the images are equally important for certain receivers. The existing semantic communication systems directly perform semantic encoding and decoding on the whole image, in which the region of interest cannot be identified. In this paper, we propose a novel semantic communication system for image transmission that can distinguish between Regions Of Interest (ROI) and Regions Of Non-Interest (RONI) based on semantic segmentation, where a semantic segmentation algorithm is used to classify each pixel of the image and distinguish ROI and RONI. The system also enables high-quality transmission of ROI with lower communication overheads by transmissions through different semantic communication networks with different bandwidth requirements. An improved metric θPSNR is proposed to evaluate the transmission accuracy of the novel semantic transmission network. Experimental results show that our proposed system achieves a significant performance improvement compared with existing approaches, namely, existing semantic communication approaches and the conventional approach without semantics.展开更多
基金supported by funding from the following sources:National Natural Science Foundation of China(U1904119)Research Programs of Henan Science and Technology Department(232102210033,232102210054)+3 种基金Chongqing Natural Science Foundation(CSTB2023NSCQ-MSX0070)Henan Province Key Research and Development Project(231111212000)Aviation Science Foundation(20230001055002)supported by Henan Center for Outstanding Overseas Scientists(GZS2022011).
文摘The key to the success of few-shot semantic segmentation(FSS)depends on the efficient use of limited annotated support set to accurately segment novel classes in the query set.Due to the few samples in the support set,FSS faces challenges such as intra-class differences,background(BG)mismatches between query and support sets,and ambiguous segmentation between the foreground(FG)and BG in the query set.To address these issues,The paper propose a multi-module network called CAMSNet,which includes four modules:the General Information Module(GIM),the Class Activation Map Aggregation(CAMA)module,the Self-Cross Attention(SCA)Block,and the Feature Fusion Module(FFM).In CAMSNet,The GIM employs an improved triplet loss,which concatenates word embedding vectors and support prototypes as anchors,and uses local support features of FG and BG as positive and negative samples to help solve the problem of intra-class differences.Then for the first time,the Class Activation Map(CAM)from the Weakly Supervised Semantic Segmentation(WSSS)is applied to FSS within the CAMA module.This method replaces the traditional use of cosine similarity to locate query information.Subsequently,the SCA Block processes the support and query features aggregated by the CAMA module,significantly enhancing the understanding of input information,leading to more accurate predictions and effectively addressing BG mismatch and ambiguous FG-BG segmentation.Finally,The FFM combines general class information with the enhanced query information to achieve accurate segmentation of the query image.Extensive Experiments on PASCAL and COCO demonstrate that-5i-20ithe CAMSNet yields superior performance and set a state-of-the-art.
基金funded by the Natural Science Foundation of the Jiangsu Higher Education Institutions of China(grant number 22KJD440001)Changzhou Science&Technology Program(grant number CJ20220232).
文摘The Internet of Vehicles (IoV) has become an important direction in the field of intelligent transportation, in which vehicle positioning is a crucial part. SLAM (Simultaneous Localization and Mapping) technology plays a crucial role in vehicle localization and navigation. Traditional Simultaneous Localization and Mapping (SLAM) systems are designed for use in static environments, and they can result in poor performance in terms of accuracy and robustness when used in dynamic environments where objects are in constant movement. To address this issue, a new real-time visual SLAM system called MG-SLAM has been developed. Based on ORB-SLAM2, MG-SLAM incorporates a dynamic target detection process that enables the detection of both known and unknown moving objects. In this process, a separate semantic segmentation thread is required to segment dynamic target instances, and the Mask R-CNN algorithm is applied on the Graphics Processing Unit (GPU) to accelerate segmentation. To reduce computational cost, only key frames are segmented to identify known dynamic objects. Additionally, a multi-view geometry method is adopted to detect unknown moving objects. The results demonstrate that MG-SLAM achieves higher precision, with an improvement from 0.2730 m to 0.0135 m in precision. Moreover, the processing time required by MG-SLAM is significantly reduced compared to other dynamic scene SLAM algorithms, which illustrates its efficacy in locating objects in dynamic scenes.
文摘Lower back pain is one of the most common medical problems in the world and it is experienced by a huge percentage of people everywhere.Due to its ability to produce a detailed view of the soft tissues,including the spinal cord,nerves,intervertebral discs,and vertebrae,Magnetic Resonance Imaging is thought to be the most effective method for imaging the spine.The semantic segmentation of vertebrae plays a major role in the diagnostic process of lumbar diseases.It is difficult to semantically partition the vertebrae in Magnetic Resonance Images from the surrounding variety of tissues,including muscles,ligaments,and intervertebral discs.U-Net is a powerful deep-learning architecture to handle the challenges of medical image analysis tasks and achieves high segmentation accuracy.This work proposes a modified U-Net architecture namely MU-Net,consisting of the Meijering convolutional layer that incorporates the Meijering filter to perform the semantic segmentation of lumbar vertebrae L1 to L5 and sacral vertebra S1.Pseudo-colour mask images were generated and used as ground truth for training the model.The work has been carried out on 1312 images expanded from T1-weighted mid-sagittal MRI images of 515 patients in the Lumbar Spine MRI Dataset publicly available from Mendeley Data.The proposed MU-Net model for the semantic segmentation of the lumbar vertebrae gives better performance with 98.79%of pixel accuracy(PA),98.66%of dice similarity coefficient(DSC),97.36%of Jaccard coefficient,and 92.55%mean Intersection over Union(mean IoU)metrics using the mentioned dataset.
基金financially supported by the Natural Science Foundation of China(42301492)the Open Fund of Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering(2022SDSJ04,2024SDSJ03)+1 种基金the Opening Fund of Key Laboratory of Geological Survey and Evaluation of Ministry of Education(GLAB 2023ZR01,GLAB2024ZR08)the Fundamental Research Funds for the Central Universities.
文摘Automatic segmentation and recognition of content and element information in color geological map are of great significance for researchers to analyze the distribution of mineral resources and predict disaster information.This article focuses on color planar raster geological map(geological maps include planar geological maps,columnar maps,and profiles).While existing deep learning approaches are often used to segment general images,their performance is limited due to complex elements,diverse regional features,and complicated backgrounds for color geological map in the domain of geoscience.To address the issue,a color geological map segmentation model is proposed that combines the Felz clustering algorithm and an improved SE-UNet deep learning network(named GeoMSeg).Firstly,a symmetrical encoder-decoder structure backbone network based on UNet is constructed,and the channel attention mechanism SENet has been incorporated to augment the network’s capacity for feature representation,enabling the model to purposefully extract map information.The SE-UNet network is employed for feature extraction from the geological map and obtain coarse segmentation results.Secondly,the Felz clustering algorithm is used for super pixel pre-segmentation of geological maps.The coarse segmentation results are refined and modified based on the super pixel pre-segmentation results to obtain the final segmentation results.This study applies GeoMSeg to the constructed dataset,and the experimental results show that the algorithm proposed in this paper has superior performance compared to other mainstream map segmentation models,with an accuracy of 91.89%and a MIoU of 71.91%.
基金supported by National Natural Science Foundation of China(No.52374155)Anhui Provincial Natural Science Foundation(No.2308085 MF218).
文摘The convolutional neural network(CNN)method based on DeepLabv3+has some problems in the semantic segmentation task of high-resolution remote sensing images,such as fixed receiving field size of feature extraction,lack of semantic information,high decoder magnification,and insufficient detail retention ability.A hierarchical feature fusion network(HFFNet)was proposed.Firstly,a combination of transformer and CNN architectures was employed for feature extraction from images of varying resolutions.The extracted features were processed independently.Subsequently,the features from the transformer and CNN were fused under the guidance of features from different sources.This fusion process assisted in restoring information more comprehensively during the decoding stage.Furthermore,a spatial channel attention module was designed in the final stage of decoding to refine features and reduce the semantic gap between shallow CNN features and deep decoder features.The experimental results showed that HFFNet had superior performance on UAVid,LoveDA,Potsdam,and Vaihingen datasets,and its cross-linking index was better than DeepLabv3+and other competing methods,showing strong generalization ability.
基金Open Access funding provided by the National Institutes of Health(NIH)The funding for this project was provided by NCATS Intramural Fund.
文摘Semantic segmentation plays a foundational role in biomedical image analysis, providing precise information about cellular, tissue, and organ structures in both biological and medical imaging modalities. Traditional approaches often fail in the face of challenges such as low contrast, morphological variability, and densely packed structures. Recent advancements in deep learning have transformed segmentation capabilities through the integration of fine-scale detail preservation, coarse-scale contextual modeling, and multi-scale feature fusion. This work provides a comprehensive analysis of state-of-the-art deep learning models, including U-Net variants, attention-based frameworks, and Transformer-integrated networks, highlighting innovations that improve accuracy, generalizability, and computational efficiency. Key architectural components such as convolution operations, shallow and deep blocks, skip connections, and hybrid encoders are examined for their roles in enhancing spatial representation and semantic consistency. We further discuss the importance of hierarchical and instance-aware segmentation and annotation in interpreting complex biological scenes and multiplexed medical images. By bridging methodological developments with diverse application domains, this paper outlines current trends and future directions for semantic segmentation, emphasizing its critical role in facilitating annotation, diagnosis, and discovery in biomedical research.
基金funded by National Natural Science Foundation of China(61603245).
文摘Semantic segmentation of remote sensing images is a critical research area in the field of remote sensing.Despite the success of Convolutional Neural Networks(CNNs),they often fail to capture inter-layer feature relationships and fully leverage contextual information,leading to the loss of important details.Additionally,due to significant intraclass variation and small inter-class differences in remote sensing images,CNNs may experience class confusion.To address these issues,we propose a novel Category-Guided Feature Collaborative Learning Network(CG-FCLNet),which enables fine-grained feature extraction and adaptive fusion.Specifically,we design a Feature Collaborative Learning Module(FCLM)to facilitate the tight interaction of multi-scale features.We also introduce a Scale-Aware Fusion Module(SAFM),which iteratively fuses features from different layers using a spatial attention mechanism,enabling deeper feature fusion.Furthermore,we design a Category-Guided Module(CGM)to extract category-aware information that guides feature fusion,ensuring that the fused featuresmore accurately reflect the semantic information of each category,thereby improving detailed segmentation.The experimental results show that CG-FCLNet achieves a Mean Intersection over Union(mIoU)of 83.46%,an mF1 of 90.87%,and an Overall Accuracy(OA)of 91.34% on the Vaihingen dataset.On the Potsdam dataset,it achieves a mIoU of 86.54%,an mF1 of 92.65%,and an OA of 91.29%.These results highlight the superior performance of CG-FCLNet compared to existing state-of-the-art methods.
基金funded by Hanoi University of Science and Technology(HUST)under project number T2023-PC-008.
文摘Due to the necessity for lightweight and efficient network models, deploying semantic segmentation models on mobile robots (MRs) is a formidable task. The fundamental limitation of the problem lies in the training performance, the ability to effectively exploit the dataset, and the ability to adapt to complex environments when deploying the model. By utilizing the knowledge distillation techniques, the article strives to overcome the above challenges with the inheritance of the advantages of both the teacher model and the student model. More precisely, the ResNet152-PSP-Net model’s characteristics are utilized to train the ResNet18-PSP-Net model. Pyramid pooling blocks are utilized to decode multi-scale feature maps, creating a complete semantic map inference. The student model not only preserves the strong segmentation performance from the teacher model but also improves the inference speed of the prediction results. The proposed method exhibits a clear advantage over conventional convolutional neural network (CNN) models, as evident from the conducted experiments. Furthermore, the proposed model also shows remarkable improvement in processing speed when compared with light-weight models such as MobileNetV2 and EfficientNet based on latency and throughput parameters. The proposed KD-SegNet model obtains an accuracy of 96.3% and a mIoU (mean Intersection over Union) of 77%, outperforming the performance of existing models by more than 15% on the same training dataset. The suggested method has an average training time that is only 0.51 times less than same field models, while still achieving comparable segmentation performance. Hence, the semantic segmentation frames are collected, forming the motion trajectory for the system in the environment. Overall, this architecture shows great promise for the development of knowledge-based systems for MR’s navigation.
基金National Natural Science Foundation of China(Grant Nos.62005049 and 62072110)Natural Science Foundation of Fujian Province(Grant No.2020J01451).
文摘Accurate segmentation of camouflage objects in aerial imagery is vital for improving the efficiency of UAV-based reconnaissance and rescue missions.However,camouflage object segmentation is increasingly challenging due to advances in both camouflage materials and biological mimicry.Although multispectral-RGB based technology shows promise,conventional dual-aperture multispectral-RGB imaging systems are constrained by imprecise and time-consuming registration and fusion across different modalities,limiting their performance.Here,we propose the Reconstructed Multispectral-RGB Fusion Network(RMRF-Net),which reconstructs RGB images into multispectral ones,enabling efficient multimodal segmentation using only an RGB camera.Specifically,RMRF-Net employs a divergentsimilarity feature correction strategy to minimize reconstruction errors and includes an efficient boundary-aware decoder to enhance object contours.Notably,we establish the first real-world aerial multispectral-RGB semantic segmentation of camouflage objects dataset,including 11 object categories.Experimental results demonstrate that RMRF-Net outperforms existing methods,achieving 17.38 FPS on the NVIDIA Jetson AGX Orin,with only a 0.96%drop in mIoU compared to the RTX 3090,showing its practical applicability in multimodal remote sensing.
文摘Real-time semantic segmentation tasks place stringent demands on network inference speed,often requiring a reduction in network depth to decrease computational load.However,shallow networks tend to exhibit degradation in feature extraction completeness and inference accuracy.Therefore,balancing high performance with real-time requirements has become a critical issue in the study of real-time semantic segmentation.To address these challenges,this paper proposes a lightweight bilateral dual-residual network.By introducing a novel residual structure combined with feature extraction and fusion modules,the proposed network significantly enhances representational capacity while reducing computational costs.Specifically,an improved compound residual structure is designed to optimize the efficiency of information propagation and feature extraction.Furthermore,the proposed feature extraction and fusion module enables the network to better capture multi-scale information in images,improving the ability to detect both detailed and global semantic features.Experimental results on the publicly available Cityscapes dataset demonstrate that the proposed lightweight dual-branch network achieves outstanding performance while maintaining low computational complexity.In particular,the network achieved a mean Intersection over Union(mIoU)of 78.4%on the Cityscapes validation set,surpassing many existing semantic segmentation models.Additionally,in terms of inference speed,the network reached 74.5 frames per second when tested on an NVIDIA GeForce RTX 3090 GPU,significantly improving real-time performance.
基金Supported by the National Natural Science Foundation of China(No.61971162,61771186)the Natural Science Foundation of Heilongjiang Province(No.PL2024F025)+2 种基金the Open Research Fund of National Mobile Communications Research Laboratory Southeast University(No.2023D07)the Outstanding Youth Program of Natural Science Foundation of Heilongjiang Province(No.YQ2020F012)the Funda-mental Scientific Research Funds of Heilongjiang Province(No.2022-KYYWF-1050).
文摘Indoor visual localization relies heavily on image retrieval to ascertain location information.However,the widespread presence and high consistency of floor patterns across different images of-ten lead to the extraction of numerous repetitive features,thereby reducing the accuracy of image retrieval.This article proposes an indoor visual localization method based on semantic segmentation and adaptive weight fusion to address the issue of ground texture interference with retrieval results.During the positioning process,an indoor semantic segmentation model is established.Semantic segmentation technology is applied to accurately delineate the ground portion of the images.Fea-ture extraction is performed on both the original database and the ground-segmented database.The vector of locally aggregated descriptors(VLAD)algorithm is then used to convert image features into a fixed-length feature representation,which improves the efficiency of image retrieval.Simul-taneously,a method for adaptive weight optimization in similarity calculation is proposed,using a-daptive weights to compute similarity for different regional features,thereby improving the accuracy of image retrieval.The experimental results indicate that this method significantly reduces ground interference and effectively utilizes ground information,thereby improving the accuracy of image retrieval.
基金supported in part by the Gansu Haizhi Characteristic Demonstration Project(No.GSHZTS2022-2).
文摘Since the introduction of vision Transformers into the computer vision field,many vision tasks such as semantic segmentation tasks,have undergone radical changes.Although Transformer enhances the correlation of each local feature of an image object in the hidden space through the attention mechanism,it is difficult for a segmentation head to accomplish the mask prediction for dense embedding of multi-category and multi-local features.We present patch prototype vision Transformer(PPFormer),a Transformer architecture for semantic segmentation based on knowledge-embedded patch prototypes.1)The hierarchical Transformer encoder can generate multi-scale and multi-layered patch features including seamless patch projection to obtain information of multiscale patches,and feature-clustered self-attention to enhance the interplay of multi-layered visual information with implicit position encodes.2)PPFormer utilizes a non-parametric prototype decoder to extract region observations which represent significant parts of the objects by unlearnable patch prototypes and then calculate similarity between patch prototypes and pixel embeddings.The proposed contrasting patch prototype alignment module,which uses new patch prototypes to update prototype bank,effectively maintains class boundaries for prototypes.For different application scenarios,we have launched PPFormer-S,PPFormer-M and PPFormer-L by expanding the scale.Experimental results demonstrate that PPFormer can outperform fully convolutional networks(FCN)-and attention-based semantic segmentation models on the PASCAL VOC 2012,ADE20k,and Cityscapes datasets.
基金supported by the National Natural Science Foundation of China(62162007)the Guizhou Provincial Basic Research Program(Natural Science)(No.QianKeHeJiChu-ZK[2024]YiBan079).
文摘Semantic segmentation has made significant breakthroughs in various application fields,but achieving both accurate and efficient segmentation with limited computational resources remains a major challenge.To this end,we propose CGMISeg,an efficient semantic segmentation architecture based on a context-guided multi-scale interaction strategy,aiming to significantly reduce computational overhead while maintaining segmentation accuracy.CGMISeg consists of three core components:context-aware attention modulation,feature reconstruction,and crossinformation fusion.Context-aware attention modulation is carefully designed to capture key contextual information through channel and spatial attention mechanisms.The feature reconstruction module reconstructs contextual information from different scales,modeling key rectangular areas by capturing critical contextual information in both horizontal and vertical directions,thereby enhancing the focus on foreground features.The cross-information fusion module aims to fuse the reconstructed high-level features with the original low-level features during upsampling,promoting multi-scale interaction and enhancing the model’s ability to handle objects at different scales.We extensively evaluated CGMISeg on ADE20K,Cityscapes,and COCO-Stuff,three widely used datasets benchmarks,and the experimental results show that CGMISeg exhibits significant advantages in segmentation performance,computational efficiency,and inference speed,clearly outperforming several mainstream methods,including SegFormer,Feedformer,and SegNext.Specifically,CGMISeg achieves 42.9%mIoU(Mean Intersection over Union)and 15.7 FPS(Frames Per Second)on the ADE20K dataset with 3.8 GFLOPs(Giga Floating-point Operations Per Second),outperforming Feedformer and SegNeXt by 3.7%and 1.8%in mIoU,respectively,while also offering reduced computational complexity and faster inference.CGMISeg strikes an excellent balance between accuracy and efficiency,significantly enhancing both computational and inference performance while maintaining high precision,showcasing exceptional practical value and strong potential for widespread applications.
基金supported in part by the National Natural Science Foundation of China[Grant number 62471075]the Major Science and Technology Project Grant of the Chongqing Municipal Education Commission[Grant number KJZD-M202301901]Graduate Innovation Fund of Chongqing[gzlcx20253235].
文摘Semantic segmentation in street scenes is a crucial technology for autonomous driving to analyze the surrounding environment.In street scenes,issues such as high image resolution caused by a large viewpoints and differences in object scales lead to a decline in real-time performance and difficulties in multi-scale feature extraction.To address this,we propose a bilateral-branch real-time semantic segmentationmethod based on semantic information distillation(BSDNet)for street scene images.The BSDNet consists of a Feature Conversion Convolutional Block(FCB),a Semantic Information Distillation Module(SIDM),and a Deep Aggregation Atrous Convolution Pyramid Pooling(DASP).FCB reduces the semantic gap between the backbone and the semantic branch.SIDM extracts high-quality semantic information fromthe Transformer branch to reduce computational costs.DASP aggregates information lost in atrous convolutions,effectively capturingmulti-scale objects.Extensive experiments conducted on Cityscapes,CamVid,and ADE20K,achieving an accuracy of 81.7% Mean Intersection over Union(mIoU)at 70.6 Frames Per Second(FPS)on Cityscapes,demonstrate that our method achieves a better balance between accuracy and inference speed.
基金supported by the STI2030-Major-Projects(No.2021ZD0200104)the National Natural Science Foundations of China under Grant 61771437.
文摘Neuronal soma segmentation plays a crucial role in neuroscience applications.However,the fine structure,such as boundaries,small-volume neuronal somata and fibers,are commonly present in cell images,which pose a challenge for accurate segmentation.In this paper,we propose a 3D semantic segmentation network for neuronal soma segmentation to address this issue.Using an encoding-decoding structure,we introduce a Multi-Scale feature extraction and Adaptive Weighting fusion module(MSAW)after each encoding block.The MSAW module can not only emphasize the fine structures via an upsampling strategy,but also provide pixel-wise weights to measure the importance of the multi-scale features.Additionally,a dynamic convolution instead of normal convolution is employed to better adapt the network to input data with different distributions.The proposed MSAW-based semantic segmentation network(MSAW-Net)was evaluated on three neuronal soma images from mouse brain and one neuronal soma image from macaque brain,demonstrating the efficiency of the proposed method.It achieved an F1 score of 91.8%on Fezf2-2A-CreER dataset,97.1%on LSL-H2B-GFP dataset,82.8%on Thy1-EGFP-Mline dataset,and 86.9%on macaque dataset,achieving improvements over the 3D U-Net model by 3.1%,3.3%,3.9%,and 2.3%,respectively.
基金funding from the following sources:National Natural Science Foundation of China(U1904119)Research Programs of Henan Science and Technology Department(232102210054)+3 种基金Chongqing Natural Science Foundation(CSTB2023NSCQ-MSX0070)Henan Province Key Research and Development Project(231111212000)Aviation Science Foundation(20230001055002)supported by Henan Center for Outstanding Overseas Scientists(GZS2022011).
文摘The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods.End-to-end model designs have gained significant attention for improving training efficiency.Most current algorithms rely on Convolutional Neural Networks(CNNs)for feature extraction.Although CNNs are proficient at capturing local features,they often struggle with global context,leading to incomplete and false Class Activation Mapping(CAM).To address these limitations,this work proposes a Contextual Prototype-Based End-to-End Weakly Supervised Semantic Segmentation(CPEWS)model,which improves feature extraction by utilizing the Vision Transformer(ViT).By incorporating its intermediate feature layers to preserve semantic information,this work introduces the Intermediate Supervised Module(ISM)to supervise the final layer’s output,reducing boundary ambiguity and mitigating issues related to incomplete activation.Additionally,the Contextual Prototype Module(CPM)generates class-specific prototypes,while the proposed Prototype Discrimination Loss and Superclass Suppression Loss guide the network’s training,(LPDL)(LSSL)effectively addressing false activation without the need for extra supervision.The CPEWS model proposed in this paper achieves state-of-the-art performance in end-to-end weakly supervised semantic segmentation without additional supervision.The validation set and test set Mean Intersection over Union(MIoU)of PASCAL VOC 2012 dataset achieved 69.8%and 72.6%,respectively.Compared with ToCo(pre trained weight ImageNet-1k),MIoU on the test set is 2.1%higher.In addition,MIoU reached 41.4%on the validation set of the MS COCO 2014 dataset.
文摘In recent years,video coding has been widely applied in the field of video image processing to remove redundant information and improve data transmission efficiency.However,during the video coding process,irrelevant objects such as background elements are often encoded due to environmental disturbances,resulting in the wastage of computational resources.Existing research on video coding efficiency optimization primarily focuses on optimizing encoding units during intra-frame or inter frame prediction after the generation of coding units,neglecting the optimization of video images before coding unit generation.To address this challenge,This work proposes an image semantic segmentation compression algorithm based on macroblock encoding,called image semantic segmentation compression algorithm based on macroblock encoding(ISSC-ME),which consists of three modules.(1)The semantic label generation module generates interesting object labels using a grid-based approach to reduce redundant coding of consecutive frames.(2)The image segmentation network module generates a semantic segmentation image using U-Net.(3)The macroblock coding module,is a block segmentation-based video encoding and decoding algorithm used to compress images and improve video transmission efficiency.Experimental results show that the proposed image semantic segmentation optimization algorithm can reduce the computational costs,and improve the overall accuracy by 1.00%and the mean intersection over union(IoU)by 1.20%.In addition,the proposed compression algorithm utilizes macroblock fusion,resulting in the image compression rate achieving 80.64%.It has been proven that the proposed algorithm greatly reduces data storage and transmission,and enables fast image compression processing at the millisecond level.
文摘Semantic segmentation of novel object categories with limited labeled data remains a challenging problem in computer vision.Few-shot segmentation methods aim to address this problem by recognizing objects from specific target classes with a few provided examples.Previous approaches for few-shot semantic segmentation typically represent target classes using class prototypes.These prototypes are matched with the features of the query set to get segmentation results.However,class prototypes are usually obtained by applying global average pooling on masked support images.Global pooling discards much structural information,which may reduce the accuracy of model predictions.To address this issue,we propose a Category-Guided Frequency Modulation(CGFM)method.CGFM is designed to learn category-specific information in the frequency space and leverage it to provide a twostage guidance for the segmentation process.First,to self-adaptively activate class-relevant frequency bands while suppressing irrelevant ones,we leverage the Dual-Perception Gaussian Band Pre-activation(DPGBP)module to generate Gaussian filters using class embedding vectors.Second,to further enhance category-relevant frequency components in activated bands,we design a Support-Guided Category Response Enhancement(SGCRE)module to effectively introduce support frequency components into the modulation of query frequency features.Experiments on the PASCAL-5^(i) and COCO-20^(i) datasets demonstrate the promising performance of our model.
基金supported by the CNPC Advanced Fundamental Research Projects(No.2023ycq06).
文摘Well logging curves serve as indicators of strata attribute changes and are frequently utilized for stratigraphic analysis and comparison.Deep learning,known for its robust feature extraction capabilities,has seen continuous adoption by scholars in the realm of well logging stratigraphic correlation tasks.Nonetheless,current deep learning algorithms often struggle to accurately capture feature changes occurring at layer boundaries within the curves.Moreover,when faced with data imbalance issues,neural networks encounter challenges in accurately modeling the one-hot encoded curve stratification positions,resulting in significant deviations between predicted and actual stratification positions.Addressing these challenges,this study proposes a novel well logging curve stratigraphic comparison algorithm based on uniformly distributed soft labels.In the training phase,a label smoothing loss function is introduced to comprehensively account for the substantial loss stemming from data imbalance and to consider the similarity between diff erent layer data.Concurrently,spatial attention and channel attention mechanisms are incorporated into the shallow and deep encoder stages of U²-Net,respectively,to better focus on changes in stratification positions.During the prediction phase,an optimized confidence threshold algorithm is proposed to constrain stratification results and solve the problem of reduced prediction accuracy because of occasional layer repetition.The proposed method is applied to real-world well logging data in oil fields.Quantitative evaluation results demonstrate that within error ranges of 1,2,and 3 m,the accuracy of well logging curve stratigraphic division reaches 87.27%,92.68%,and 95.08%,respectively,thus validating the eff ectiveness of the algorithm presented in this paper.
基金supported in part by collaborative research with Toyota Motor Corporation,in part by ROIS NII Open Collaborative Research under Grant 21S0601,in part by JSPS KAKENHI under Grants 20H00592,21H03424.
文摘With the rapid development of artificial intelligence and the widespread use of the Internet of Things, semantic communication, as an emerging communication paradigm, has been attracting great interest. Taking image transmission as an example, from the semantic communication's view, not all pixels in the images are equally important for certain receivers. The existing semantic communication systems directly perform semantic encoding and decoding on the whole image, in which the region of interest cannot be identified. In this paper, we propose a novel semantic communication system for image transmission that can distinguish between Regions Of Interest (ROI) and Regions Of Non-Interest (RONI) based on semantic segmentation, where a semantic segmentation algorithm is used to classify each pixel of the image and distinguish ROI and RONI. The system also enables high-quality transmission of ROI with lower communication overheads by transmissions through different semantic communication networks with different bandwidth requirements. An improved metric θPSNR is proposed to evaluate the transmission accuracy of the novel semantic transmission network. Experimental results show that our proposed system achieves a significant performance improvement compared with existing approaches, namely, existing semantic communication approaches and the conventional approach without semantics.
