Camouflaged Object Detection(COD)aims to identify objects that share highly similar patterns—such as texture,intensity,and color—with their surrounding environment.Due to their intrinsic resemblance to the backgroun...Camouflaged Object Detection(COD)aims to identify objects that share highly similar patterns—such as texture,intensity,and color—with their surrounding environment.Due to their intrinsic resemblance to the background,camouflaged objects often exhibit vague boundaries and varying scales,making it challenging to accurately locate targets and delineate their indistinct edges.To address this,we propose a novel camouflaged object detection network called Edge-Guided and Multi-scale Fusion Network(EGMFNet),which leverages edge-guided multi-scale integration for enhanced performance.The model incorporates two innovative components:a Multi-scale Fusion Module(MSFM)and an Edge-Guided Attention Module(EGA).These designs exploit multi-scale features to uncover subtle cues between candidate objects and the background while emphasizing camouflaged object boundaries.Moreover,recognizing the rich contextual information in fused features,we introduce a Dual-Branch Global Context Module(DGCM)to refine features using extensive global context,thereby generatingmore informative representations.Experimental results on four benchmark datasets demonstrate that EGMFNet outperforms state-of-the-art methods across five evaluation metrics.Specifically,on COD10K,our EGMFNet-P improves F_(β)by 4.8 points and reduces mean absolute error(MAE)by 0.006 compared with ZoomNeXt;on NC4K,it achieves a 3.6-point increase in F_(β).OnCAMO and CHAMELEON,it obtains 4.5-point increases in F_(β),respectively.These consistent gains substantiate the superiority and robustness of EGMFNet.展开更多
Driven by rapid advances in deep learning,object detection has been widely adopted across diverse application scenarios.However,in low-light conditions,critical visual cues of target objects are severely degraded,posi...Driven by rapid advances in deep learning,object detection has been widely adopted across diverse application scenarios.However,in low-light conditions,critical visual cues of target objects are severely degraded,posing a significant challenge for accurate low-light object detection.Existing methods struggle to preserve discriminative features while maintaining semantic consistency between low-light and normal-light images.For this purpose,this study proposes a DL-YOLO model specially tailored for low-light detection.To mitigate target feature attenuation introduced by repeated downsampling,we design aMulti-Scale FeatureConvolution(MSF-Conv)module that captures rich,multi-level details via multi-scale feature learning,thereby reducing model complexity and computational cost.For feature fusion,we integrated the C3k2-DWRmodule by embedding the Dilation-wise Residual(DWR)mechanism into the 2-core optimized Cross Stage Partial(C3)framework,achieving efficient feature integration.In addition,we replace conventional localization losses with WIoU(Weighted Intersection over Union),which dynamically adjusts gradient gain according to sample quality,thereby improving localization robustness and precision.Experiments on the ExDark dataset demonstrate that DL-YOLO delivers strong low-light detection performance.The relevant code is published at https://github.com/cym0997/DL-YOLO.展开更多
Semantic segmentation for mixed scenes of aerial remote sensing and road traffic is one of the key technologies for visual perception of flying cars.The State-of-the-Art(SOTA)semantic segmentation methods have made re...Semantic segmentation for mixed scenes of aerial remote sensing and road traffic is one of the key technologies for visual perception of flying cars.The State-of-the-Art(SOTA)semantic segmentation methods have made remarkable achievements in both fine-grained segmentation and real-time performance.However,when faced with the huge differences in scale and semantic categories brought about by the mixed scenes of aerial remote sensing and road traffic,they still face great challenges and there is little related research.Addressing the above issue,this paper proposes a semantic segmentation model specifically for mixed datasets of aerial remote sensing and road traffic scenes.First,a novel decoding-recoding multi-scale feature iterative refinement structure is proposed,which utilizes the re-integration and continuous enhancement of multi-scale information to effectively deal with the huge scale differences between cross-domain scenes,while using a fully convolutional structure to ensure the lightweight and real-time requirements.Second,a welldesigned cross-window attention mechanism combined with a global information integration decoding block forms an enhanced global context perception,which can effectively capture the long-range dependencies and multi-scale global context information of different scenes,thereby achieving fine-grained semantic segmentation.The proposed method is tested on a large-scale mixed dataset of aerial remote sensing and road traffic scenes.The results confirm that it can effectively deal with the problem of large-scale differences in cross-domain scenes.Its segmentation accuracy surpasses that of the SOTA methods,which meets the real-time requirements.展开更多
Most Convolutional Neural Network(CNN)interpretation techniques visualize only the dominant cues that the model relies on,but there is no guarantee that these represent all the evidence the model uses for classificati...Most Convolutional Neural Network(CNN)interpretation techniques visualize only the dominant cues that the model relies on,but there is no guarantee that these represent all the evidence the model uses for classification.This limitation becomes critical when hidden secondary cues—potentially more meaningful than the visualized ones—remain undiscovered.This study introduces CasCAM(Cascaded Class Activation Mapping)to address this fundamental limitation through counterfactual reasoning.By asking“if this dominant cue were absent,what other evidence would the model use?”,CasCAM progressively masks the most salient features and systematically uncovers the hierarchy of classification evidence hidden beneath them.Experimental results demonstrate that CasCAM effectively discovers the full spectrum of reasoning evidence and can be universally applied with nine existing interpretation methods.展开更多
Transportation systems are experiencing a significant transformation due to the integration of advanced technologies, including artificial intelligence and machine learning. In the context of intelligent transportatio...Transportation systems are experiencing a significant transformation due to the integration of advanced technologies, including artificial intelligence and machine learning. In the context of intelligent transportation systems (ITS) and Advanced Driver Assistance Systems (ADAS), the development of efficient and reliable traffic light detection mechanisms is crucial for enhancing road safety and traffic management. This paper presents an optimized convolutional neural network (CNN) framework designed to detect traffic lights in real-time within complex urban environments. Leveraging multi-scale pyramid feature maps, the proposed model addresses key challenges such as the detection of small, occluded, and low-resolution traffic lights amidst complex backgrounds. The integration of dilated convolutions, Region of Interest (ROI) alignment, and Soft Non-Maximum Suppression (Soft-NMS) further improves detection accuracy and reduces false positives. By optimizing computational efficiency and parameter complexity, the framework is designed to operate seamlessly on embedded systems, ensuring robust performance in real-world applications. Extensive experiments using real-world datasets demonstrate that our model significantly outperforms existing methods, providing a scalable solution for ITS and ADAS applications. This research contributes to the advancement of Artificial Intelligence-driven (AI-driven) pattern recognition in transportation systems and offers a mathematical approach to improving efficiency and safety in logistics and transportation networks.展开更多
Deep Learning has been widely used to model soft sensors in modern industrial processes with nonlinear variables and uncertainty.Due to the outstanding ability for high-level feature extraction,stacked autoencoder(SAE...Deep Learning has been widely used to model soft sensors in modern industrial processes with nonlinear variables and uncertainty.Due to the outstanding ability for high-level feature extraction,stacked autoencoder(SAE)has been widely used to improve the model accuracy of soft sensors.However,with the increase of network layers,SAE may encounter serious information loss issues,which affect the modeling performance of soft sensors.Besides,there are typically very few labeled samples in the data set,which brings challenges to traditional neural networks to solve.In this paper,a multi-scale feature fused stacked autoencoder(MFF-SAE)is suggested for feature representation related to hierarchical output,where stacked autoencoder,mutual information(MI)and multi-scale feature fusion(MFF)strategies are integrated.Based on correlation analysis between output and input variables,critical hidden variables are extracted from the original variables in each autoencoder's input layer,which are correspondingly given varying weights.Besides,an integration strategy based on multi-scale feature fusion is adopted to mitigate the impact of information loss with the deepening of the network layers.Then,the MFF-SAE method is designed and stacked to form deep networks.Two practical industrial processes are utilized to evaluate the performance of MFF-SAE.Results from simulations indicate that in comparison to other cutting-edge techniques,the proposed method may considerably enhance the accuracy of soft sensor modeling,where the suggested method reduces the root mean square error(RMSE)by 71.8%,17.1%and 64.7%,15.1%,respectively.展开更多
An improved model based on you only look once version 8(YOLOv8)is proposed to solve the problem of low detection accuracy due to the diversity of object sizes in optical remote sensing images.Firstly,the feature pyram...An improved model based on you only look once version 8(YOLOv8)is proposed to solve the problem of low detection accuracy due to the diversity of object sizes in optical remote sensing images.Firstly,the feature pyramid network(FPN)structure of the original YOLOv8 mode is replaced by the generalized-FPN(GFPN)structure in GiraffeDet to realize the"cross-layer"and"cross-scale"adaptive feature fusion,to enrich the semantic information and spatial information on the feature map to improve the target detection ability of the model.Secondly,a pyramid-pool module of multi atrous spatial pyramid pooling(MASPP)is designed by using the idea of atrous convolution and feature pyramid structure to extract multi-scale features,so as to improve the processing ability of the model for multi-scale objects.The experimental results show that the detection accuracy of the improved YOLOv8 model on DIOR dataset is 92%and mean average precision(mAP)is 87.9%,respectively 3.5%and 1.7%higher than those of the original model.It is proved the detection and classification ability of the proposed model on multi-dimensional optical remote sensing target has been improved.展开更多
The fusion of infrared and visible images should emphasize the salient targets in the infrared image while preserving the textural details of the visible images.To meet these requirements,an autoencoder-based method f...The fusion of infrared and visible images should emphasize the salient targets in the infrared image while preserving the textural details of the visible images.To meet these requirements,an autoencoder-based method for infrared and visible image fusion is proposed.The encoder designed according to the optimization objective consists of a base encoder and a detail encoder,which is used to extract low-frequency and high-frequency information from the image.This extraction may lead to some information not being captured,so a compensation encoder is proposed to supplement the missing information.Multi-scale decomposition is also employed to extract image features more comprehensively.The decoder combines low-frequency,high-frequency and supplementary information to obtain multi-scale features.Subsequently,the attention strategy and fusion module are introduced to perform multi-scale fusion for image reconstruction.Experimental results on three datasets show that the fused images generated by this network effectively retain salient targets while being more consistent with human visual perception.展开更多
Globally,diabetic retinopathy(DR)is the primary cause of blindness,affecting millions of people worldwide.This widespread impact underscores the critical need for reliable and precise diagnostic techniques to ensure p...Globally,diabetic retinopathy(DR)is the primary cause of blindness,affecting millions of people worldwide.This widespread impact underscores the critical need for reliable and precise diagnostic techniques to ensure prompt diagnosis and effective treatment.Deep learning-based automated diagnosis for diabetic retinopathy can facilitate early detection and treatment.However,traditional deep learning models that focus on local views often learn feature representations that are less discriminative at the semantic level.On the other hand,models that focus on global semantic-level information might overlook critical,subtle local pathological features.To address this issue,we propose an adaptive multi-scale feature fusion network called(AMSFuse),which can adaptively combine multi-scale global and local features without compromising their individual representation.Specifically,our model incorporates global features for extracting high-level contextual information from retinal images.Concurrently,local features capture fine-grained details,such as microaneurysms,hemorrhages,and exudates,which are critical for DR diagnosis.These global and local features are adaptively fused using a fusion block,followed by an Integrated Attention Mechanism(IAM)that refines the fused features by emphasizing relevant regions,thereby enhancing classification accuracy for DR classification.Our model achieves 86.3%accuracy on the APTOS dataset and 96.6%RFMiD,both of which are comparable to state-of-the-art methods.展开更多
Detecting abnormal cervical cells is crucial for early identification and timely treatment of cervical cancer.However,this task is challenging due to the morphological similarities between abnormal and normal cells an...Detecting abnormal cervical cells is crucial for early identification and timely treatment of cervical cancer.However,this task is challenging due to the morphological similarities between abnormal and normal cells and the significant variations in cell size.Pathologists often refer to surrounding cells to identify abnormalities.To emulate this slide examination behavior,this study proposes a Multi-Scale Feature Fusion Network(MSFF-Net)for detecting cervical abnormal cells.MSFF-Net employs a Cross-Scale Pooling Model(CSPM)to effectively capture diverse features and contextual information,ranging from local details to the overall structure.Additionally,a Multi-Scale Fusion Attention(MSFA)module is introduced to mitigate the impact of cell size variations by adaptively fusing local and global information at different scales.To handle the complex environment of cervical cell images,such as cell adhesion and overlapping,the Inner-CIoU loss function is utilized to more precisely measure the overlap between bounding boxes,thereby improving detection accuracy in such scenarios.Experimental results on the Comparison detector dataset demonstrate that MSFF-Net achieves a mean average precision(mAP)of 63.2%,outperforming state-of-the-art methods while maintaining a relatively small number of parameters(26.8 M).This study highlights the effectiveness of multi-scale feature fusion in enhancing the detection of cervical abnormal cells,contributing to more accurate and efficient cervical cancer screening.展开更多
With the rapid growth of socialmedia,the spread of fake news has become a growing problem,misleading the public and causing significant harm.As social media content is often composed of both images and text,the use of...With the rapid growth of socialmedia,the spread of fake news has become a growing problem,misleading the public and causing significant harm.As social media content is often composed of both images and text,the use of multimodal approaches for fake news detection has gained significant attention.To solve the problems existing in previous multi-modal fake news detection algorithms,such as insufficient feature extraction and insufficient use of semantic relations between modes,this paper proposes the MFFFND-Co(Multimodal Feature Fusion Fake News Detection with Co-Attention Block)model.First,the model deeply explores the textual content,image content,and frequency domain features.Then,it employs a Co-Attention mechanism for cross-modal fusion.Additionally,a semantic consistency detectionmodule is designed to quantify semantic deviations,thereby enhancing the performance of fake news detection.Experimentally verified on two commonly used datasets,Twitter and Weibo,the model achieved F1 scores of 90.0% and 94.0%,respectively,significantly outperforming the pre-modified MFFFND(Multimodal Feature Fusion Fake News Detection with Attention Block)model and surpassing other baseline models.This improves the accuracy of detecting fake information in artificial intelligence detection and engineering software detection.展开更多
To solve the problems of redundant feature information,the insignificant difference in feature representation,and low recognition accuracy of the fine-grained image,based on the ResNeXt50 model,an MSFResNet network mo...To solve the problems of redundant feature information,the insignificant difference in feature representation,and low recognition accuracy of the fine-grained image,based on the ResNeXt50 model,an MSFResNet network model is proposed by fusing multi-scale feature information.Firstly,a multi-scale feature extraction module is designed to obtain multi-scale information on feature images by using different scales of convolution kernels.Meanwhile,the channel attention mechanism is used to increase the global information acquisition of the network.Secondly,the feature images processed by the multi-scale feature extraction module are fused with the deep feature images through short links to guide the full learning of the network,thus reducing the loss of texture details of the deep network feature images,and improving network generalization ability and recognition accuracy.Finally,the validity of the MSFResNet model is verified using public datasets and applied to wild mushroom identification.Experimental results show that compared with ResNeXt50 network model,the accuracy of the MSFResNet model is improved by 6.01%on the FGVC-Aircraft common dataset.It achieves 99.13%classification accuracy on the wild mushroom dataset,which is 0.47%higher than ResNeXt50.Furthermore,the experimental results of the thermal map show that the MSFResNet model significantly reduces the interference of background information,making the network focus on the location of the main body of wild mushroom,which can effectively improve the accuracy of wild mushroom identification.展开更多
With the rapid expansion of drone applications,accurate detection of objects in aerial imagery has become crucial for intelligent transportation,urban management,and emergency rescue missions.However,existing methods ...With the rapid expansion of drone applications,accurate detection of objects in aerial imagery has become crucial for intelligent transportation,urban management,and emergency rescue missions.However,existing methods face numerous challenges in practical deployment,including scale variation handling,feature degradation,and complex backgrounds.To address these issues,we propose Edge-enhanced and Detail-Capturing You Only Look Once(EHDC-YOLO),a novel framework for object detection in Unmanned Aerial Vehicle(UAV)imagery.Based on the You Only Look Once version 11 nano(YOLOv11n)baseline,EHDC-YOLO systematically introduces several architectural enhancements:(1)a Multi-Scale Edge Enhancement(MSEE)module that leverages multi-scale pooling and edge information to enhance boundary feature extraction;(2)an Enhanced Feature Pyramid Network(EFPN)that integrates P2-level features with Cross Stage Partial(CSP)structures and OmniKernel convolutions for better fine-grained representation;and(3)Dynamic Head(DyHead)with multi-dimensional attention mechanisms for enhanced cross-scale modeling and perspective adaptability.Comprehensive experiments on the Vision meets Drones for Detection(VisDrone-DET)2019 dataset demonstrate that EHDC-YOLO achieves significant improvements,increasing mean Average Precision(mAP)@0.5 from 33.2%to 46.1%(an absolute improvement of 12.9 percentage points)and mAP@0.5:0.95 from 19.5%to 28.0%(an absolute improvement of 8.5 percentage points)compared with the YOLOv11n baseline,while maintaining a reasonable parameter count(2.81 M vs the baseline’s 2.58 M).Further ablation studies confirm the effectiveness of each proposed component,while visualization results highlight EHDC-YOLO’s superior performance in detecting objects and handling occlusions in complex drone scenarios.展开更多
Tomato is a major economic crop worldwide,and diseases on tomato leaves can significantly reduce both yield and quality.Traditional manual inspection is inefficient and highly subjective,making it difficult to meet th...Tomato is a major economic crop worldwide,and diseases on tomato leaves can significantly reduce both yield and quality.Traditional manual inspection is inefficient and highly subjective,making it difficult to meet the requirements of early disease identification in complex natural environments.To address this issue,this study proposes an improved YOLO11-based model,YOLO-SPDNet(Scale Sequence Fusion,Position-Channel Attention,and Dual Enhancement Network).The model integrates the SEAM(Self-Ensembling Attention Mechanism)semantic enhancement module,the MLCA(Mixed Local Channel Attention)lightweight attention mechanism,and the SPA(Scale-Position-Detail Awareness)module composed of SSFF(Scale Sequence Feature Fusion),TFE(Triple Feature Encoding),and CPAM(Channel and Position Attention Mechanism).These enhancements strengthen fine-grained lesion detection while maintaining model lightweightness.Experimental results show that YOLO-SPDNet achieves an accuracy of 91.8%,a recall of 86.5%,and an mAP@0.5 of 90.6%on the test set,with a computational complexity of 12.5 GFLOPs.Furthermore,the model reaches a real-time inference speed of 987 FPS,making it suitable for deployment on mobile agricultural terminals and online monitoring systems.Comparative analysis and ablation studies further validate the reliability and practical applicability of the proposed model in complex natural scenes.展开更多
By integrating self-localization,environment mapping,and dynamic object tracking into a unified framework,visual simultaneous localization and mapping with multiple object tracking(SLAMMOT)enhances decision-making and...By integrating self-localization,environment mapping,and dynamic object tracking into a unified framework,visual simultaneous localization and mapping with multiple object tracking(SLAMMOT)enhances decision-making and interaction capabilities in applications such as autonomous driving,robotic navigation,and augmented reality.While numerous outstanding visual SLAMMOT methods have been proposed,the majority rely only on point features,overlooking the abundant and stable planar features in artificial objects that can provide valuable constraints.To address this limitation,we propose OP(object planar)-SLAM,an RGB-D SLAMMOT system that leverages planar features to improve object pose estimation and reconstruction accuracy.Specifically,we introduce an accurate object planar feature extraction and association method using normal images,alongside a novel object bundle adjustment framework that incorporates planar constraints for enhanced optimization.The proposed system is evaluated on both synthetic and public real-world datasets,including Oxford multimotion dataset(OMD)and KITTI tracking dataset.Especially on the OMD,where planar features are prominent,our method improves object pose estimation accuracy by approximately 60%.Extensive experiments demonstrate its effectiveness in enhancing object pose estimation and reconstruction,achieving notable performance compared with existing methods.Furthermore,OP-SLAM runs in real time,making it suitable for practical robots and augmented reality applications.展开更多
Ocean observations are inherently characterized by irregular temporal and spatial distributions,as well as heterogeneous spatial resolutions and error characteristics arising from the use of diverse observational plat...Ocean observations are inherently characterized by irregular temporal and spatial distributions,as well as heterogeneous spatial resolutions and error characteristics arising from the use of diverse observational platforms and techniques.To enable their application across a broad range of scientific and practical problems,it is essential to map these heterogeneous datasets into temporally and spatially consistent gridded products.Optimal Interpolation remains the most widely adopted algorithm for the mapping of oceanographic data.Two principal implementations of the optimal interpolation algorithm are commonly employed.The first,known as the basic optimal interpolation,is derived from the theory of optimal estimation and involves computationally intensive matrix operations,posing significant challenges when applied to high-dimensional problems.The second,referred to as the point-wise optimal interpolation,reduces computational complexity through point-wise estimation,thereby circumventing high-dimensional operations;however,this approach results in a substantially higher overall computational cost.In this study,a novel optimal interpolation algorithm is proposed that utilizes the Kronecker product to approximate the background error covariance matrix.This formulation enables the decomposition of high-dimensional matrix operations into smaller,computationally tractable sub-problems,thereby improving the scalability of optimal interpolation for large spatial domains with dense observational coverage.Building upon this framework,a multi-scale optimal interpolation method is further developed to enhance the integration of observational datasets with widely varying spatial resolutions,thereby improving the accuracy and applicability of the resulting gridded products.展开更多
Generative image steganography is a technique that directly generates stego images from secret infor-mation.Unlike traditional methods,it theoretically resists steganalysis because there is no cover image.Currently,th...Generative image steganography is a technique that directly generates stego images from secret infor-mation.Unlike traditional methods,it theoretically resists steganalysis because there is no cover image.Currently,the existing generative image steganography methods generally have good steganography performance,but there is still potential room for enhancing both the quality of stego images and the accuracy of secret information extraction.Therefore,this paper proposes a generative image steganography algorithm based on attribute feature transformation and invertible mapping rule.Firstly,the reference image is disentangled by a content and an attribute encoder to obtain content features and attribute features,respectively.Then,a mean mapping rule is introduced to map the binary secret information into a noise vector,conforming to the distribution of attribute features.This noise vector is input into the generator to produce the attribute transformed stego image with the content feature of the reference image.Additionally,we design an adversarial loss,a reconstruction loss,and an image diversity loss to train the proposed model.Experimental results demonstrate that the stego images generated by the proposed method are of high quality,with an average extraction accuracy of 99.4%for the hidden information.Furthermore,since the stego image has a uniform distribution similar to the attribute-transformed image without secret information,it effectively resists both subjective and objective steganalysis.展开更多
In modern electromagnetic environment, radar emitter signal recognition is an important research topic. On the basis of multi-resolution wavelet analysis, an adaptive radar emitter signal recognition method based on m...In modern electromagnetic environment, radar emitter signal recognition is an important research topic. On the basis of multi-resolution wavelet analysis, an adaptive radar emitter signal recognition method based on multi-scale wavelet entropy feature extraction and feature weighting was proposed. With the only priori knowledge of signal to noise ratio(SNR), the method of extracting multi-scale wavelet entropy features of wavelet coefficients from different received signals were combined with calculating uneven weight factor and stability weight factor of the extracted multi-dimensional characteristics. Radar emitter signals of different modulation types and different parameters modulated were recognized through feature weighting and feature fusion. Theoretical analysis and simulation results show that the presented algorithm has a high recognition rate. Additionally, when the SNR is greater than-4 d B, the correct recognition rate is higher than 93%. Hence, the proposed algorithm has great application value.展开更多
Feature extraction of signals plays an important role in classification problems because of data dimension reduction property and potential improvement of a classification accuracy rate. Principal component analysis (...Feature extraction of signals plays an important role in classification problems because of data dimension reduction property and potential improvement of a classification accuracy rate. Principal component analysis (PCA), wavelets transform or Fourier transform methods are often used for feature extraction. In this paper, we propose a multi-scale PCA, which combines discrete wavelet transform, and PCA for feature extraction of signals in both the spatial and temporal domains. Our study shows that the multi-scale PCA combined with the proposed new classification methods leads to high classification accuracy for the considered signals.展开更多
Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware reso...Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware resources. To address this issue, the MobileNetV1 network was developed, which employs depthwise convolution to reduce network complexity. MobileNetV1 employs a stride of 2 in several convolutional layers to decrease the spatial resolution of feature maps, thereby lowering computational costs. However, this stride setting can lead to a loss of spatial information, particularly affecting the detection and representation of smaller objects or finer details in images. To maintain the trade-off between complexity and model performance, a lightweight convolutional neural network with hierarchical multi-scale feature fusion based on the MobileNetV1 network is proposed. The network consists of two main subnetworks. The first subnetwork uses a depthwise dilated separable convolution (DDSC) layer to learn imaging features with fewer parameters, which results in a lightweight and computationally inexpensive network. Furthermore, depthwise dilated convolution in DDSC layer effectively expands the field of view of filters, allowing them to incorporate a larger context. The second subnetwork is a hierarchical multi-scale feature fusion (HMFF) module that uses parallel multi-resolution branches architecture to process the input feature map in order to extract the multi-scale feature information of the input image. Experimental results on the CIFAR-10, Malaria, and KvasirV1 datasets demonstrate that the proposed method is efficient, reducing the network parameters and computational cost by 65.02% and 39.78%, respectively, while maintaining the network performance compared to the MobileNetV1 baseline.展开更多
基金financially supported byChongqingUniversity of Technology Graduate Innovation Foundation(Grant No.gzlcx20253267).
文摘Camouflaged Object Detection(COD)aims to identify objects that share highly similar patterns—such as texture,intensity,and color—with their surrounding environment.Due to their intrinsic resemblance to the background,camouflaged objects often exhibit vague boundaries and varying scales,making it challenging to accurately locate targets and delineate their indistinct edges.To address this,we propose a novel camouflaged object detection network called Edge-Guided and Multi-scale Fusion Network(EGMFNet),which leverages edge-guided multi-scale integration for enhanced performance.The model incorporates two innovative components:a Multi-scale Fusion Module(MSFM)and an Edge-Guided Attention Module(EGA).These designs exploit multi-scale features to uncover subtle cues between candidate objects and the background while emphasizing camouflaged object boundaries.Moreover,recognizing the rich contextual information in fused features,we introduce a Dual-Branch Global Context Module(DGCM)to refine features using extensive global context,thereby generatingmore informative representations.Experimental results on four benchmark datasets demonstrate that EGMFNet outperforms state-of-the-art methods across five evaluation metrics.Specifically,on COD10K,our EGMFNet-P improves F_(β)by 4.8 points and reduces mean absolute error(MAE)by 0.006 compared with ZoomNeXt;on NC4K,it achieves a 3.6-point increase in F_(β).OnCAMO and CHAMELEON,it obtains 4.5-point increases in F_(β),respectively.These consistent gains substantiate the superiority and robustness of EGMFNet.
文摘Driven by rapid advances in deep learning,object detection has been widely adopted across diverse application scenarios.However,in low-light conditions,critical visual cues of target objects are severely degraded,posing a significant challenge for accurate low-light object detection.Existing methods struggle to preserve discriminative features while maintaining semantic consistency between low-light and normal-light images.For this purpose,this study proposes a DL-YOLO model specially tailored for low-light detection.To mitigate target feature attenuation introduced by repeated downsampling,we design aMulti-Scale FeatureConvolution(MSF-Conv)module that captures rich,multi-level details via multi-scale feature learning,thereby reducing model complexity and computational cost.For feature fusion,we integrated the C3k2-DWRmodule by embedding the Dilation-wise Residual(DWR)mechanism into the 2-core optimized Cross Stage Partial(C3)framework,achieving efficient feature integration.In addition,we replace conventional localization losses with WIoU(Weighted Intersection over Union),which dynamically adjusts gradient gain according to sample quality,thereby improving localization robustness and precision.Experiments on the ExDark dataset demonstrate that DL-YOLO delivers strong low-light detection performance.The relevant code is published at https://github.com/cym0997/DL-YOLO.
基金supported by the National Key Research and Development of China(No.2022YFB2503400).
文摘Semantic segmentation for mixed scenes of aerial remote sensing and road traffic is one of the key technologies for visual perception of flying cars.The State-of-the-Art(SOTA)semantic segmentation methods have made remarkable achievements in both fine-grained segmentation and real-time performance.However,when faced with the huge differences in scale and semantic categories brought about by the mixed scenes of aerial remote sensing and road traffic,they still face great challenges and there is little related research.Addressing the above issue,this paper proposes a semantic segmentation model specifically for mixed datasets of aerial remote sensing and road traffic scenes.First,a novel decoding-recoding multi-scale feature iterative refinement structure is proposed,which utilizes the re-integration and continuous enhancement of multi-scale information to effectively deal with the huge scale differences between cross-domain scenes,while using a fully convolutional structure to ensure the lightweight and real-time requirements.Second,a welldesigned cross-window attention mechanism combined with a global information integration decoding block forms an enhanced global context perception,which can effectively capture the long-range dependencies and multi-scale global context information of different scenes,thereby achieving fine-grained semantic segmentation.The proposed method is tested on a large-scale mixed dataset of aerial remote sensing and road traffic scenes.The results confirm that it can effectively deal with the problem of large-scale differences in cross-domain scenes.Its segmentation accuracy surpasses that of the SOTA methods,which meets the real-time requirements.
基金supported by the Basic Science Research Program through the National Research Foundation of Korea(NRF),funded by the Ministry of Education(RS-2023-00249743).
文摘Most Convolutional Neural Network(CNN)interpretation techniques visualize only the dominant cues that the model relies on,but there is no guarantee that these represent all the evidence the model uses for classification.This limitation becomes critical when hidden secondary cues—potentially more meaningful than the visualized ones—remain undiscovered.This study introduces CasCAM(Cascaded Class Activation Mapping)to address this fundamental limitation through counterfactual reasoning.By asking“if this dominant cue were absent,what other evidence would the model use?”,CasCAM progressively masks the most salient features and systematically uncovers the hierarchy of classification evidence hidden beneath them.Experimental results demonstrate that CasCAM effectively discovers the full spectrum of reasoning evidence and can be universally applied with nine existing interpretation methods.
基金funded by the Deanship of Scientific Research at Northern Border University,Arar,Saudi Arabia through research group No.(RG-NBU-2022-1234).
文摘Transportation systems are experiencing a significant transformation due to the integration of advanced technologies, including artificial intelligence and machine learning. In the context of intelligent transportation systems (ITS) and Advanced Driver Assistance Systems (ADAS), the development of efficient and reliable traffic light detection mechanisms is crucial for enhancing road safety and traffic management. This paper presents an optimized convolutional neural network (CNN) framework designed to detect traffic lights in real-time within complex urban environments. Leveraging multi-scale pyramid feature maps, the proposed model addresses key challenges such as the detection of small, occluded, and low-resolution traffic lights amidst complex backgrounds. The integration of dilated convolutions, Region of Interest (ROI) alignment, and Soft Non-Maximum Suppression (Soft-NMS) further improves detection accuracy and reduces false positives. By optimizing computational efficiency and parameter complexity, the framework is designed to operate seamlessly on embedded systems, ensuring robust performance in real-world applications. Extensive experiments using real-world datasets demonstrate that our model significantly outperforms existing methods, providing a scalable solution for ITS and ADAS applications. This research contributes to the advancement of Artificial Intelligence-driven (AI-driven) pattern recognition in transportation systems and offers a mathematical approach to improving efficiency and safety in logistics and transportation networks.
基金supported by the National Key Research and Development Program of China(2023YFB3307800)National Natural Science Foundation of China(62394343,62373155)+2 种基金Major Science and Technology Project of Xinjiang(No.2022A01006-4)State Key Laboratory of Industrial Control Technology,China(Grant No.ICT2024A26)Fundamental Research Funds for the Central Universities.
文摘Deep Learning has been widely used to model soft sensors in modern industrial processes with nonlinear variables and uncertainty.Due to the outstanding ability for high-level feature extraction,stacked autoencoder(SAE)has been widely used to improve the model accuracy of soft sensors.However,with the increase of network layers,SAE may encounter serious information loss issues,which affect the modeling performance of soft sensors.Besides,there are typically very few labeled samples in the data set,which brings challenges to traditional neural networks to solve.In this paper,a multi-scale feature fused stacked autoencoder(MFF-SAE)is suggested for feature representation related to hierarchical output,where stacked autoencoder,mutual information(MI)and multi-scale feature fusion(MFF)strategies are integrated.Based on correlation analysis between output and input variables,critical hidden variables are extracted from the original variables in each autoencoder's input layer,which are correspondingly given varying weights.Besides,an integration strategy based on multi-scale feature fusion is adopted to mitigate the impact of information loss with the deepening of the network layers.Then,the MFF-SAE method is designed and stacked to form deep networks.Two practical industrial processes are utilized to evaluate the performance of MFF-SAE.Results from simulations indicate that in comparison to other cutting-edge techniques,the proposed method may considerably enhance the accuracy of soft sensor modeling,where the suggested method reduces the root mean square error(RMSE)by 71.8%,17.1%and 64.7%,15.1%,respectively.
基金supported by the National Natural Science Foundation of China(No.62241109)the Tianjin Science and Technology Commissioner Project(No.20YDTPJC01110)。
文摘An improved model based on you only look once version 8(YOLOv8)is proposed to solve the problem of low detection accuracy due to the diversity of object sizes in optical remote sensing images.Firstly,the feature pyramid network(FPN)structure of the original YOLOv8 mode is replaced by the generalized-FPN(GFPN)structure in GiraffeDet to realize the"cross-layer"and"cross-scale"adaptive feature fusion,to enrich the semantic information and spatial information on the feature map to improve the target detection ability of the model.Secondly,a pyramid-pool module of multi atrous spatial pyramid pooling(MASPP)is designed by using the idea of atrous convolution and feature pyramid structure to extract multi-scale features,so as to improve the processing ability of the model for multi-scale objects.The experimental results show that the detection accuracy of the improved YOLOv8 model on DIOR dataset is 92%and mean average precision(mAP)is 87.9%,respectively 3.5%and 1.7%higher than those of the original model.It is proved the detection and classification ability of the proposed model on multi-dimensional optical remote sensing target has been improved.
基金Supported by the Henan Province Key Research and Development Project(231111211300)the Central Government of Henan Province Guides Local Science and Technology Development Funds(Z20231811005)+2 种基金Henan Province Key Research and Development Project(231111110100)Henan Provincial Outstanding Foreign Scientist Studio(GZS2024006)Henan Provincial Joint Fund for Scientific and Technological Research and Development Plan(Application and Overcoming Technical Barriers)(242103810028)。
文摘The fusion of infrared and visible images should emphasize the salient targets in the infrared image while preserving the textural details of the visible images.To meet these requirements,an autoencoder-based method for infrared and visible image fusion is proposed.The encoder designed according to the optimization objective consists of a base encoder and a detail encoder,which is used to extract low-frequency and high-frequency information from the image.This extraction may lead to some information not being captured,so a compensation encoder is proposed to supplement the missing information.Multi-scale decomposition is also employed to extract image features more comprehensively.The decoder combines low-frequency,high-frequency and supplementary information to obtain multi-scale features.Subsequently,the attention strategy and fusion module are introduced to perform multi-scale fusion for image reconstruction.Experimental results on three datasets show that the fused images generated by this network effectively retain salient targets while being more consistent with human visual perception.
基金supported by the National Natural Science Foundation of China(No.62376287)the International Science and Technology Innovation Joint Base of Machine Vision and Medical Image Processing in Hunan Province(2021CB1013)the Natural Science Foundation of Hunan Province(Nos.2022JJ30762,2023JJ70016).
文摘Globally,diabetic retinopathy(DR)is the primary cause of blindness,affecting millions of people worldwide.This widespread impact underscores the critical need for reliable and precise diagnostic techniques to ensure prompt diagnosis and effective treatment.Deep learning-based automated diagnosis for diabetic retinopathy can facilitate early detection and treatment.However,traditional deep learning models that focus on local views often learn feature representations that are less discriminative at the semantic level.On the other hand,models that focus on global semantic-level information might overlook critical,subtle local pathological features.To address this issue,we propose an adaptive multi-scale feature fusion network called(AMSFuse),which can adaptively combine multi-scale global and local features without compromising their individual representation.Specifically,our model incorporates global features for extracting high-level contextual information from retinal images.Concurrently,local features capture fine-grained details,such as microaneurysms,hemorrhages,and exudates,which are critical for DR diagnosis.These global and local features are adaptively fused using a fusion block,followed by an Integrated Attention Mechanism(IAM)that refines the fused features by emphasizing relevant regions,thereby enhancing classification accuracy for DR classification.Our model achieves 86.3%accuracy on the APTOS dataset and 96.6%RFMiD,both of which are comparable to state-of-the-art methods.
基金funded by the China Chongqing Municipal Science and Technology Bureau,grant numbers 2024TIAD-CYKJCXX0121,2024NSCQ-LZX0135Chongqing Municipal Commission of Housing and Urban-Rural Development,grant number CKZ2024-87+3 种基金the Chongqing University of Technology graduate education high-quality development project,grant number gzlsz202401the Chongqing University of Technology-Chongqing LINGLUE Technology Co.,Ltd.,Electronic Information(Artificial Intelligence)graduate joint training basethe Postgraduate Education and Teaching Reform Research Project in Chongqing,grant number yjg213116the Chongqing University of Technology-CISDI Chongqing Information Technology Co.,Ltd.,Computer Technology graduate joint training base.
文摘Detecting abnormal cervical cells is crucial for early identification and timely treatment of cervical cancer.However,this task is challenging due to the morphological similarities between abnormal and normal cells and the significant variations in cell size.Pathologists often refer to surrounding cells to identify abnormalities.To emulate this slide examination behavior,this study proposes a Multi-Scale Feature Fusion Network(MSFF-Net)for detecting cervical abnormal cells.MSFF-Net employs a Cross-Scale Pooling Model(CSPM)to effectively capture diverse features and contextual information,ranging from local details to the overall structure.Additionally,a Multi-Scale Fusion Attention(MSFA)module is introduced to mitigate the impact of cell size variations by adaptively fusing local and global information at different scales.To handle the complex environment of cervical cell images,such as cell adhesion and overlapping,the Inner-CIoU loss function is utilized to more precisely measure the overlap between bounding boxes,thereby improving detection accuracy in such scenarios.Experimental results on the Comparison detector dataset demonstrate that MSFF-Net achieves a mean average precision(mAP)of 63.2%,outperforming state-of-the-art methods while maintaining a relatively small number of parameters(26.8 M).This study highlights the effectiveness of multi-scale feature fusion in enhancing the detection of cervical abnormal cells,contributing to more accurate and efficient cervical cancer screening.
基金supported by Communication University of China(HG23035)partly supported by the Fundamental Research Funds for the Central Universities(CUC230A013).
文摘With the rapid growth of socialmedia,the spread of fake news has become a growing problem,misleading the public and causing significant harm.As social media content is often composed of both images and text,the use of multimodal approaches for fake news detection has gained significant attention.To solve the problems existing in previous multi-modal fake news detection algorithms,such as insufficient feature extraction and insufficient use of semantic relations between modes,this paper proposes the MFFFND-Co(Multimodal Feature Fusion Fake News Detection with Co-Attention Block)model.First,the model deeply explores the textual content,image content,and frequency domain features.Then,it employs a Co-Attention mechanism for cross-modal fusion.Additionally,a semantic consistency detectionmodule is designed to quantify semantic deviations,thereby enhancing the performance of fake news detection.Experimentally verified on two commonly used datasets,Twitter and Weibo,the model achieved F1 scores of 90.0% and 94.0%,respectively,significantly outperforming the pre-modified MFFFND(Multimodal Feature Fusion Fake News Detection with Attention Block)model and surpassing other baseline models.This improves the accuracy of detecting fake information in artificial intelligence detection and engineering software detection.
基金supported by National Natural Science Foundation of China(No.61862037)Lanzhou Jiaotong University Tianyou Innovation Team Project(No.TY202002)。
文摘To solve the problems of redundant feature information,the insignificant difference in feature representation,and low recognition accuracy of the fine-grained image,based on the ResNeXt50 model,an MSFResNet network model is proposed by fusing multi-scale feature information.Firstly,a multi-scale feature extraction module is designed to obtain multi-scale information on feature images by using different scales of convolution kernels.Meanwhile,the channel attention mechanism is used to increase the global information acquisition of the network.Secondly,the feature images processed by the multi-scale feature extraction module are fused with the deep feature images through short links to guide the full learning of the network,thus reducing the loss of texture details of the deep network feature images,and improving network generalization ability and recognition accuracy.Finally,the validity of the MSFResNet model is verified using public datasets and applied to wild mushroom identification.Experimental results show that compared with ResNeXt50 network model,the accuracy of the MSFResNet model is improved by 6.01%on the FGVC-Aircraft common dataset.It achieves 99.13%classification accuracy on the wild mushroom dataset,which is 0.47%higher than ResNeXt50.Furthermore,the experimental results of the thermal map show that the MSFResNet model significantly reduces the interference of background information,making the network focus on the location of the main body of wild mushroom,which can effectively improve the accuracy of wild mushroom identification.
文摘With the rapid expansion of drone applications,accurate detection of objects in aerial imagery has become crucial for intelligent transportation,urban management,and emergency rescue missions.However,existing methods face numerous challenges in practical deployment,including scale variation handling,feature degradation,and complex backgrounds.To address these issues,we propose Edge-enhanced and Detail-Capturing You Only Look Once(EHDC-YOLO),a novel framework for object detection in Unmanned Aerial Vehicle(UAV)imagery.Based on the You Only Look Once version 11 nano(YOLOv11n)baseline,EHDC-YOLO systematically introduces several architectural enhancements:(1)a Multi-Scale Edge Enhancement(MSEE)module that leverages multi-scale pooling and edge information to enhance boundary feature extraction;(2)an Enhanced Feature Pyramid Network(EFPN)that integrates P2-level features with Cross Stage Partial(CSP)structures and OmniKernel convolutions for better fine-grained representation;and(3)Dynamic Head(DyHead)with multi-dimensional attention mechanisms for enhanced cross-scale modeling and perspective adaptability.Comprehensive experiments on the Vision meets Drones for Detection(VisDrone-DET)2019 dataset demonstrate that EHDC-YOLO achieves significant improvements,increasing mean Average Precision(mAP)@0.5 from 33.2%to 46.1%(an absolute improvement of 12.9 percentage points)and mAP@0.5:0.95 from 19.5%to 28.0%(an absolute improvement of 8.5 percentage points)compared with the YOLOv11n baseline,while maintaining a reasonable parameter count(2.81 M vs the baseline’s 2.58 M).Further ablation studies confirm the effectiveness of each proposed component,while visualization results highlight EHDC-YOLO’s superior performance in detecting objects and handling occlusions in complex drone scenarios.
基金Tianmin Tianyuan Boutique Vegetable Industry Technology Service Station(Grant No.2024120011003081)Development of Environmental Monitoring and Traceability System for Wuqing Agricultural Production Areas(Grant No.2024120011001866)。
文摘Tomato is a major economic crop worldwide,and diseases on tomato leaves can significantly reduce both yield and quality.Traditional manual inspection is inefficient and highly subjective,making it difficult to meet the requirements of early disease identification in complex natural environments.To address this issue,this study proposes an improved YOLO11-based model,YOLO-SPDNet(Scale Sequence Fusion,Position-Channel Attention,and Dual Enhancement Network).The model integrates the SEAM(Self-Ensembling Attention Mechanism)semantic enhancement module,the MLCA(Mixed Local Channel Attention)lightweight attention mechanism,and the SPA(Scale-Position-Detail Awareness)module composed of SSFF(Scale Sequence Feature Fusion),TFE(Triple Feature Encoding),and CPAM(Channel and Position Attention Mechanism).These enhancements strengthen fine-grained lesion detection while maintaining model lightweightness.Experimental results show that YOLO-SPDNet achieves an accuracy of 91.8%,a recall of 86.5%,and an mAP@0.5 of 90.6%on the test set,with a computational complexity of 12.5 GFLOPs.Furthermore,the model reaches a real-time inference speed of 987 FPS,making it suitable for deployment on mobile agricultural terminals and online monitoring systems.Comparative analysis and ablation studies further validate the reliability and practical applicability of the proposed model in complex natural scenes.
基金Supported by Major Science and Technology Project of Hubei Province(2022AAA009)。
文摘By integrating self-localization,environment mapping,and dynamic object tracking into a unified framework,visual simultaneous localization and mapping with multiple object tracking(SLAMMOT)enhances decision-making and interaction capabilities in applications such as autonomous driving,robotic navigation,and augmented reality.While numerous outstanding visual SLAMMOT methods have been proposed,the majority rely only on point features,overlooking the abundant and stable planar features in artificial objects that can provide valuable constraints.To address this limitation,we propose OP(object planar)-SLAM,an RGB-D SLAMMOT system that leverages planar features to improve object pose estimation and reconstruction accuracy.Specifically,we introduce an accurate object planar feature extraction and association method using normal images,alongside a novel object bundle adjustment framework that incorporates planar constraints for enhanced optimization.The proposed system is evaluated on both synthetic and public real-world datasets,including Oxford multimotion dataset(OMD)and KITTI tracking dataset.Especially on the OMD,where planar features are prominent,our method improves object pose estimation accuracy by approximately 60%.Extensive experiments demonstrate its effectiveness in enhancing object pose estimation and reconstruction,achieving notable performance compared with existing methods.Furthermore,OP-SLAM runs in real time,making it suitable for practical robots and augmented reality applications.
基金The National Key Research and Development Program of China under contract No.2022YFF0801404.
文摘Ocean observations are inherently characterized by irregular temporal and spatial distributions,as well as heterogeneous spatial resolutions and error characteristics arising from the use of diverse observational platforms and techniques.To enable their application across a broad range of scientific and practical problems,it is essential to map these heterogeneous datasets into temporally and spatially consistent gridded products.Optimal Interpolation remains the most widely adopted algorithm for the mapping of oceanographic data.Two principal implementations of the optimal interpolation algorithm are commonly employed.The first,known as the basic optimal interpolation,is derived from the theory of optimal estimation and involves computationally intensive matrix operations,posing significant challenges when applied to high-dimensional problems.The second,referred to as the point-wise optimal interpolation,reduces computational complexity through point-wise estimation,thereby circumventing high-dimensional operations;however,this approach results in a substantially higher overall computational cost.In this study,a novel optimal interpolation algorithm is proposed that utilizes the Kronecker product to approximate the background error covariance matrix.This formulation enables the decomposition of high-dimensional matrix operations into smaller,computationally tractable sub-problems,thereby improving the scalability of optimal interpolation for large spatial domains with dense observational coverage.Building upon this framework,a multi-scale optimal interpolation method is further developed to enhance the integration of observational datasets with widely varying spatial resolutions,thereby improving the accuracy and applicability of the resulting gridded products.
基金supported in part by the National Natural Science Foundation of China(Nos.62202234,62401270)the China Postdoctoral Science Foundation(No.2023M741778)the Natural Science Foundation of Jiangsu Province(Nos.BK20240706,BK20240694).
文摘Generative image steganography is a technique that directly generates stego images from secret infor-mation.Unlike traditional methods,it theoretically resists steganalysis because there is no cover image.Currently,the existing generative image steganography methods generally have good steganography performance,but there is still potential room for enhancing both the quality of stego images and the accuracy of secret information extraction.Therefore,this paper proposes a generative image steganography algorithm based on attribute feature transformation and invertible mapping rule.Firstly,the reference image is disentangled by a content and an attribute encoder to obtain content features and attribute features,respectively.Then,a mean mapping rule is introduced to map the binary secret information into a noise vector,conforming to the distribution of attribute features.This noise vector is input into the generator to produce the attribute transformed stego image with the content feature of the reference image.Additionally,we design an adversarial loss,a reconstruction loss,and an image diversity loss to train the proposed model.Experimental results demonstrate that the stego images generated by the proposed method are of high quality,with an average extraction accuracy of 99.4%for the hidden information.Furthermore,since the stego image has a uniform distribution similar to the attribute-transformed image without secret information,it effectively resists both subjective and objective steganalysis.
基金Project(61301095)supported by the National Natural Science Foundation of ChinaProject(QC2012C070)supported by Heilongjiang Provincial Natural Science Foundation for the Youth,ChinaProjects(HEUCF130807,HEUCFZ1129)supported by the Fundamental Research Funds for the Central Universities of China
文摘In modern electromagnetic environment, radar emitter signal recognition is an important research topic. On the basis of multi-resolution wavelet analysis, an adaptive radar emitter signal recognition method based on multi-scale wavelet entropy feature extraction and feature weighting was proposed. With the only priori knowledge of signal to noise ratio(SNR), the method of extracting multi-scale wavelet entropy features of wavelet coefficients from different received signals were combined with calculating uneven weight factor and stability weight factor of the extracted multi-dimensional characteristics. Radar emitter signals of different modulation types and different parameters modulated were recognized through feature weighting and feature fusion. Theoretical analysis and simulation results show that the presented algorithm has a high recognition rate. Additionally, when the SNR is greater than-4 d B, the correct recognition rate is higher than 93%. Hence, the proposed algorithm has great application value.
文摘Feature extraction of signals plays an important role in classification problems because of data dimension reduction property and potential improvement of a classification accuracy rate. Principal component analysis (PCA), wavelets transform or Fourier transform methods are often used for feature extraction. In this paper, we propose a multi-scale PCA, which combines discrete wavelet transform, and PCA for feature extraction of signals in both the spatial and temporal domains. Our study shows that the multi-scale PCA combined with the proposed new classification methods leads to high classification accuracy for the considered signals.
文摘Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware resources. To address this issue, the MobileNetV1 network was developed, which employs depthwise convolution to reduce network complexity. MobileNetV1 employs a stride of 2 in several convolutional layers to decrease the spatial resolution of feature maps, thereby lowering computational costs. However, this stride setting can lead to a loss of spatial information, particularly affecting the detection and representation of smaller objects or finer details in images. To maintain the trade-off between complexity and model performance, a lightweight convolutional neural network with hierarchical multi-scale feature fusion based on the MobileNetV1 network is proposed. The network consists of two main subnetworks. The first subnetwork uses a depthwise dilated separable convolution (DDSC) layer to learn imaging features with fewer parameters, which results in a lightweight and computationally inexpensive network. Furthermore, depthwise dilated convolution in DDSC layer effectively expands the field of view of filters, allowing them to incorporate a larger context. The second subnetwork is a hierarchical multi-scale feature fusion (HMFF) module that uses parallel multi-resolution branches architecture to process the input feature map in order to extract the multi-scale feature information of the input image. Experimental results on the CIFAR-10, Malaria, and KvasirV1 datasets demonstrate that the proposed method is efficient, reducing the network parameters and computational cost by 65.02% and 39.78%, respectively, while maintaining the network performance compared to the MobileNetV1 baseline.
