Precipitation nowcasting is of great importance for disaster prevention and mitigation.However,precipitation is a complex spatio-temporal phenomenon influenced by various underlying physical factors.Even slight change...Precipitation nowcasting is of great importance for disaster prevention and mitigation.However,precipitation is a complex spatio-temporal phenomenon influenced by various underlying physical factors.Even slight changes in the initial precipitation field can have a significant impact on the future precipitation patterns,making the nowcasting of short-term high-resolution precipitation a major challenge.Traditional deep learning methods often have difficulty capturing the long-term spatial dependence of precipitation and are usually at a low resolution.To address these issues,based upon the Simpler yet Better Video Prediction(SimVP)framework,we proposed a deep generative neural network that incorporates the Simple Parameter-Free Attention Module(SimAM)and Generative Adversarial Networks(GANs)for short-term high-resolution precipitation event forecasting.Through an adversarial training strategy,critical precipitation features were extracted from complex radar echo images.During the adversarial learning process,the dynamic competition between the generator and the discriminator could continuously enhance the model in prediction accuracy and resolution for short-term precipitation.Experimental results demonstrate that the proposed method could effectively forecast short-term precipitation events on various scales and showed the best overall performance among existing methods.展开更多
Current you only look once(YOLO)-based algorithm model is facing the challenge of overwhelming parameters and calculation complexity under the printed circuit board(PCB)defect detection application scenario.In order t...Current you only look once(YOLO)-based algorithm model is facing the challenge of overwhelming parameters and calculation complexity under the printed circuit board(PCB)defect detection application scenario.In order to solve this problem,we propose a new method,which combined the lightweight network mobile vision transformer(Mobile Vi T)with the convolutional block attention module(CBAM)mechanism and the new regression loss function.This method needed less computation resources,making it more suitable for embedded edge detection devices.Meanwhile,the new loss function improved the positioning accuracy of the bounding box and enhanced the robustness of the model.In addition,experiments on public datasets demonstrate that the improved model achieves an average accuracy of 87.9%across six typical defect detection tasks,while reducing computational costs by nearly 90%.It significantly reduces the model's computational requirements while maintaining accuracy,ensuring reliable performance for edge deployment.展开更多
This paper proposes a lightweight traffic sign detection system based on you only look once(YOLO).Firstly,the classification to fusion(C2f)structure is integrated into the backbone network,employing deformable convolu...This paper proposes a lightweight traffic sign detection system based on you only look once(YOLO).Firstly,the classification to fusion(C2f)structure is integrated into the backbone network,employing deformable convolution and bi-directional feature pyramid network(BiFPN)_Concat to improve the adaptability of the network.Secondly,the simple attention module(SimAm)is embedded to prioritize key features and reduce the complexity of the model after the C2f layer at the end of the backbone network.Next,the focal efficient intersection over union(EloU)is introduced to adjust the weights of challenging samples.Finally,we accomplish the design and deployment for the mobile app.The results demonstrate improvements,with the F1 score of 0.8987,mean average precision(mAP)@0.5 of 98.8%,mAP@0.5:0.95 of 75.6%,and the detection speed of 50 frames per second(FPS).展开更多
With the development of anti-virus technology,malicious documents have gradually become the main pathway of Advanced Persistent Threat(APT)attacks,therefore,the development of effective malicious document classifiers ...With the development of anti-virus technology,malicious documents have gradually become the main pathway of Advanced Persistent Threat(APT)attacks,therefore,the development of effective malicious document classifiers has become particularly urgent.Currently,detection methods based on document structure and behavioral features encounter challenges in feature engineering,these methods not only have limited accuracy,but also consume large resources,and usually can only detect documents in specific formats,which lacks versatility and adaptability.To address such problems,this paper proposes a novel malicious document detection method-visualizing documents as GGE images(Grayscale,Grayscale matrix,Entropy).The GGE method visualizes the original byte sequence of the malicious document as a grayscale image,the information entropy sequence of the document as an entropy image,and at the same time,the grayscale level co-occurrence matrix and the texture and spatial information stored in it are converted into grayscale matrix image,and fuses the three types of images to get the GGE color image.The Convolutional Block Attention Module-EfficientNet-B0(CBAM-EfficientNet-B0)model is then used for classification,combining transfer learning and applying the pre-trained model on the ImageNet dataset to the feature extraction process of GGE images.As shown in the experimental results,the GGE method has superior performance compared with other methods,which is suitable for detecting malicious documents in different formats,and achieves an accuracy of 99.44%and 97.39%on Portable Document Format(PDF)and office datasets,respectively,and consumes less time during the detection process,which can be effectively applied to the task of detecting malicious documents in real-time.展开更多
In order to solve the challenge of breast cancer region segmentation,we improved the U-Net.The convolutional block attention module with prioritized attention(CBAM-PA)and dilated transformer(Dformer)modules were desig...In order to solve the challenge of breast cancer region segmentation,we improved the U-Net.The convolutional block attention module with prioritized attention(CBAM-PA)and dilated transformer(Dformer)modules were designed to replace the convolutional layers at the encoding side in the base U-Net,the input logic of the U-Net was improved by dynamically adjusting the input size of each layer,and the short connections in the U-Net were replaced with crosslayer connections to enhance the image restoration capability at the decoding side.On the breast ultrasound images(BUSI)dataset,we obtain a Dice coefficient of 0.8031 and an intersection-over-union(IoU)value of 0.7362.The experimental results show that the proposed enhancement method effectively improves the accuracy and quality of breast cancer lesion region segmentation.展开更多
We propose a hierarchical multi-scale attention mechanism-based model in response to the low accuracy and inefficient manual classification of existing oceanic biological image classification methods. Firstly, the hie...We propose a hierarchical multi-scale attention mechanism-based model in response to the low accuracy and inefficient manual classification of existing oceanic biological image classification methods. Firstly, the hierarchical efficient multi-scale attention(H-EMA) module is designed for lightweight feature extraction, achieving outstanding performance at a relatively low cost. Secondly, an improved EfficientNetV2 block is used to integrate information from different scales better and enhance inter-layer message passing. Furthermore, introducing the convolutional block attention module(CBAM) enhances the model's perception of critical features, optimizing its generalization ability. Lastly, Focal Loss is introduced to adjust the weights of complex samples to address the issue of imbalanced categories in the dataset, further improving the model's performance. The model achieved 96.11% accuracy on the intertidal marine organism dataset of Nanji Islands and 84.78% accuracy on the CIFAR-100 dataset, demonstrating its strong generalization ability to meet the demands of oceanic biological image classification.展开更多
This paper proposes an automated detection framework for transmission facilities using a featureattention multi-scale robustness network(FAMSR-Net)with high-fidelity virtual images.The proposed framework exhibits thre...This paper proposes an automated detection framework for transmission facilities using a featureattention multi-scale robustness network(FAMSR-Net)with high-fidelity virtual images.The proposed framework exhibits three key characteristics.First,virtual images of the transmission facilities generated using StyleGAN2-ADA are co-trained with real images.This enables the neural network to learn various features of transmission facilities to improve the detection performance.Second,the convolutional block attention module is deployed in FAMSR-Net to effectively extract features from images and construct multi-dimensional feature maps,enabling the neural network to perform precise object detection in various environments.Third,an effective bounding box optimization method called Scylla-IoU is deployed on FAMSR-Net,considering the intersection over union,center point distance,angle,and shape of the bounding box.This enables the detection of power facilities of various sizes accurately.Extensive experiments demonstrated that FAMSRNet outperforms other neural networks in detecting power facilities.FAMSR-Net also achieved the highest detection accuracy when virtual images of the transmission facilities were co-trained in the training phase.The proposed framework is effective for the scheduled operation and maintenance of transmission facilities because an optical camera is currently the most promising tool for unmanned aerial vehicles.This ultimately contributes to improved inspection efficiency,reduced maintenance risks,and more reliable power delivery across extensive transmission facilities.展开更多
With the rapid development of digital communication and the widespread use of the Internet of Things,multi-view image compression has attracted increasing attention as a fundamental technology for image data communica...With the rapid development of digital communication and the widespread use of the Internet of Things,multi-view image compression has attracted increasing attention as a fundamental technology for image data communication.Multi-view image compression aims to improve compression efficiency by leveraging correlations between images.However,the requirement of synchronization and inter-image communication at the encoder side poses significant challenges,especially for constrained devices.In this study,we introduce a novel distributed image compression model based on the attention mechanism to address the challenges associated with the availability of side information only during decoding.Our model integrates an encoder network,a quantization module,and a decoder network,to ensure both high compression performance and high-quality image reconstruction.The encoder uses a deep Convolutional Neural Network(CNN)to extract high-level features from the input image,which then pass through the quantization module for further compression before undergoing lossless entropy coding.The decoder of our model consists of three main components that allow us to fully exploit the information within and between images on the decoder side.Specifically,we first introduce a channel-spatial attention module to capture and refine information within individual image feature maps.Second,we employ a semi-coupled convolution module to extract both shared and specific information in images.Finally,a cross-attention module is employed to fuse mutual information extracted from side information.The effectiveness of our model is validated on various datasets,including KITTI Stereo and Cityscapes.The results highlight the superior compression capabilities of our method,surpassing state-of-the-art techniques.展开更多
Vehicle re-identification involves matching images of vehicles across varying camera views.The diversity of camera locations along different roadways leads to significant intra-class variation and only minimal inter-c...Vehicle re-identification involves matching images of vehicles across varying camera views.The diversity of camera locations along different roadways leads to significant intra-class variation and only minimal inter-class similarity in the collected vehicle images,which increases the complexity of re-identification tasks.To tackle these challenges,this study proposes AG-GCN(Attention-Guided Graph Convolutional Network),a novel framework integrating several pivotal components.Initially,AG-GCN embeds a lightweight attention module within the ResNet-50 structure to learn feature weights automatically,thereby improving the representation of vehicle features globally by highlighting salient features and suppressing extraneous ones.Moreover,AG-GCN adopts a graph-based structure to encapsulate deep local features.A graph convolutional network then amalgamates these features to understand the relationships among vehicle-related characteristics.Subsequently,we amalgamate feature maps from both the attention and graph-based branches for a more comprehensive representation of vehicle features.The framework then gauges feature similarities and ranks them,thus enhancing the accuracy of vehicle re-identification.Comprehensive qualitative and quantitative analyses on two publicly available datasets verify the efficacy of AG-GCN in addressing intra-class and inter-class variability issues.展开更多
To address the issues of slow diagnostic speed,low accuracy,and poor generalization performance in traditional rolling bearing fault diagnosis methods,we propose a rolling bearing fault diagnosis method based on Marko...To address the issues of slow diagnostic speed,low accuracy,and poor generalization performance in traditional rolling bearing fault diagnosis methods,we propose a rolling bearing fault diagnosis method based on Markov Transition Field(MTF)image encoding combined with a lightweight convolutional neural network that integrates a Convolutional Block Attention Module(CBAM-LCNN).Specifically,we first use the Markov Transition Field to convert the original one-dimensional vibration signals of rolling bearings into two-dimensional images.Then,we construct a lightweight convolutional neural network incorporating the convolutional attention module(CBAM-LCNN).Finally,the two-dimensional images obtained from MTF mapping are fed into the CBAM-LCNN network for image feature extraction and fault diagnosis.We validate the effectiveness of the proposed method on the bearing fault datasets from Guangdong University of Petrochemical Technology’s multi-stage centrifugal fan and Case Western Reserve University.Experimental results show that,compared to other advanced baseline methods,the proposed rolling bearing fault diagnosis method offers faster diagnostic speed and higher diagnostic accuracy.In addition,we conducted experiments on the Xi’an Jiaotong University rolling bearing dataset,achieving excellent results in bearing fault diagnosis.These results validate the strong generalization performance of the proposed method.The method presented in this paper not only effectively diagnoses faults in rolling bearings but also serves as a reference for fault diagnosis in other equipment.展开更多
With the continuous development of artificial intelligence and machine learning techniques,there have been effective methods supporting the work of dermatologist in the field of skin cancer detection.However,object si...With the continuous development of artificial intelligence and machine learning techniques,there have been effective methods supporting the work of dermatologist in the field of skin cancer detection.However,object significant challenges have been presented in accurately segmenting melanomas in dermoscopic images due to the objects that could interfere human observations,such as bubbles and scales.To address these challenges,we propose a dual U-Net network framework for skin melanoma segmentation.In our proposed architecture,we introduce several innovative components that aim to enhance the performance and capabilities of the traditional U-Net.First,we establish a novel framework that links two simplified U-Nets,enabling more comprehensive information exchange and feature integration throughout the network.Second,after cascading the second U-Net,we introduce a skip connection between the decoder and encoder networks,and incorporate a modified receptive field block(MRFB),which is designed to capture multi-scale spatial information.Third,to further enhance the feature representation capabilities,we add a multi-path convolution block attention module(MCBAM)to the first two layers of the first U-Net encoding,and integrate a new squeeze-and-excitation(SE)mechanism with residual connections in the second U-Net.To illustrate the performance of our proposed model,we conducted comprehensive experiments on widely recognized skin datasets.On the ISIC-2017 dataset,the IoU value of our proposed model increased from 0.6406 to 0.6819 and the Dice coefficient increased from 0.7625 to 0.8023.On the ISIC-2018 dataset,the IoU value of proposed model also improved from 0.7138 to 0.7709,while the Dice coefficient increased from 0.8285 to 0.8665.Furthermore,the generalization experiments conducted on the jaw cyst dataset from Quzhou People’s Hospital further verified the outstanding segmentation performance of the proposed model.These findings collectively affirm the potential of our approach as a valuable tool in supporting clinical decision-making in the field of skin cancer detection,as well as advancing research in medical image analysis.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
Multimodal image fusion plays an important role in image analysis and applications.Multimodal medical image fusion helps to combine contrast features from two or more input imaging modalities to represent fused inform...Multimodal image fusion plays an important role in image analysis and applications.Multimodal medical image fusion helps to combine contrast features from two or more input imaging modalities to represent fused information in a single image.One of the critical clinical applications of medical image fusion is to fuse anatomical and functional modalities for rapid diagnosis of malignant tissues.This paper proposes a multimodal medical image fusion network(MMIF-Net)based on multiscale hybrid attention.The method first decomposes the original image to obtain the low-rank and significant parts.Then,to utilize the features at different scales,we add amultiscalemechanism that uses three filters of different sizes to extract the features in the encoded network.Also,a hybrid attention module is introduced to obtain more image details.Finally,the fused images are reconstructed by decoding the network.We conducted experiments with clinical images from brain computed tomography/magnetic resonance.The experimental results show that the multimodal medical image fusion network method based on multiscale hybrid attention works better than other advanced fusion methods.展开更多
Pest detection techniques are helpful in reducing the frequency and scale of pest outbreaks;however,their application in the actual agricultural production process is still challenging owing to the problems of intersp...Pest detection techniques are helpful in reducing the frequency and scale of pest outbreaks;however,their application in the actual agricultural production process is still challenging owing to the problems of interspecies similarity,multi-scale,and background complexity of pests.To address these problems,this study proposes an FD-YOLO pest target detection model.The FD-YOLO model uses a Fully Connected Feature Pyramid Network(FC-FPN)instead of a PANet in the neck,which can adaptively fuse multi-scale information so that the model can retain small-scale target features in the deep layer,enhance large-scale target features in the shallow layer,and enhance the multiplexing of effective features.A dual self-attention module(DSA)is then embedded in the C3 module of the neck,which captures the dependencies between the information in both spatial and channel dimensions,effectively enhancing global features.We selected 16 types of pests that widely damage field crops in the IP102 pest dataset,which were used as our dataset after data supplementation and enhancement.The experimental results showed that FD-YOLO’s mAP@0.5 improved by 6.8%compared to YOLOv5,reaching 82.6%and 19.1%–5%better than other state-of-the-art models.This method provides an effective new approach for detecting similar or multiscale pests in field crops.展开更多
The generation of high-quality,realistic face generation has emerged as a key field of research in computer vision.This paper proposes a robust approach that combines a Super-Resolution Generative Adversarial Network(...The generation of high-quality,realistic face generation has emerged as a key field of research in computer vision.This paper proposes a robust approach that combines a Super-Resolution Generative Adversarial Network(SRGAN)with a Pyramid Attention Module(PAM)to enhance the quality of deep face generation.The SRGAN framework is designed to improve the resolution of generated images,addressing common challenges such as blurriness and a lack of intricate details.The Pyramid Attention Module further complements the process by focusing on multi-scale feature extraction,enabling the network to capture finer details and complex facial features more effectively.The proposed method was trained and evaluated over 100 epochs on the CelebA dataset,demonstrating consistent improvements in image quality and a marked decrease in generator and discriminator losses,reflecting the model’s capacity to learn and synthesize high-quality images effectively,given adequate computational resources.Experimental outcome demonstrates that the SRGAN model with PAM module has outperformed,yielding an aggregate discriminator loss of 0.055 for real,0.043 for fake,and a generator loss of 10.58 after training for 100 epochs.The model has yielded an structural similarity index measure of 0.923,that has outperformed the other models that are considered in the current study for analysis.展开更多
An improved cycle-consistent generative adversarial network(CycleGAN) method for defect data augmentation based on feature fusion and self attention residual module is proposed to address the insufficiency of defect s...An improved cycle-consistent generative adversarial network(CycleGAN) method for defect data augmentation based on feature fusion and self attention residual module is proposed to address the insufficiency of defect sample data for light guide plate(LGP) in production,as well as the problem of minor defects.Two optimizations are made to the generator of CycleGAN:fusion of low resolution features obtained from partial up-sampling and down-sampling with high-resolution features,combination of self attention mechanism with residual network structure to replace the original residual module.Qualitative and quantitative experiments were conducted to compare different data augmentation methods,and the results show that the defect images of the LGP generated by the improved network were more realistic,and the accuracy of the you only look once version 5(YOLOv5) detection network for the LGP was improved by 5.6%,proving the effectiveness and accuracy of the proposed method.展开更多
In order to meet the requirements of accurate identification of surface defects on copper strip in industrial production,a detection model of surface defects based on machine vision,CSC-YOLO,is proposed.The model uses...In order to meet the requirements of accurate identification of surface defects on copper strip in industrial production,a detection model of surface defects based on machine vision,CSC-YOLO,is proposed.The model uses YOLOv4-tiny as the benchmark network.First,K-means clustering is introduced into the benchmark network to obtain anchor frames that match the self-built dataset.Second,a cross-region fusion module is introduced in the backbone network to solve the difficult target recognition problem by fusing contextual semantic information.Third,the spatial pyramid pooling-efficient channel attention network(SPP-E)module is introduced in the path aggregation network(PANet)to enhance the extraction of features.Fourth,to prevent the loss of channel information,a lightweight attention mechanism is introduced to improve the performance of the network.Finally,the performance of the model is improved by adding adjustment factors to correct the loss function for the dimensional characteristics of the surface defects.CSC-YOLO was tested on the self-built dataset of surface defects in copper strip,and the experimental results showed that the mAP of the model can reach 93.58%,which is a 3.37% improvement compared with the benchmark network,and FPS,although decreasing compared with the benchmark network,reached 104.CSC-YOLO takes into account the real-time requirements of copper strip production.The comparison experiments with Faster RCNN,SSD300,YOLOv3,YOLOv4,Resnet50-YOLOv4,YOLOv5s,YOLOv7,and other algorithms show that the algorithm obtains a faster computation speed while maintaining a higher detection accuracy.展开更多
Aim: To diagnose COVID-19 more efficiently and more correctly, this study proposed a novel attention network forCOVID-19 (ANC). Methods: Two datasets were used in this study. An 18-way data augmentation was proposed t...Aim: To diagnose COVID-19 more efficiently and more correctly, this study proposed a novel attention network forCOVID-19 (ANC). Methods: Two datasets were used in this study. An 18-way data augmentation was proposed toavoid overfitting. Then, convolutional block attention module (CBAM) was integrated to our model, the structureof which is fine-tuned. Finally, Grad-CAM was used to provide an explainable diagnosis. Results: The accuracyof our ANC methods on two datasets are 96.32% ± 1.06%, and 96.00% ± 1.03%, respectively. Conclusions: Thisproposed ANC method is superior to 9 state-of-the-art approaches.展开更多
基金Supported by the National Natural Science Foundation of China(No.42306214)the Postdoctoral Innovative Talents Support Program of Shandong Province(No.SDBX2022026)+1 种基金the China Postdoctoral Science Foundation(No.2023M733533)the Special Research Assistant Project of the Chinese Academy of Sciences in 2022。
文摘Precipitation nowcasting is of great importance for disaster prevention and mitigation.However,precipitation is a complex spatio-temporal phenomenon influenced by various underlying physical factors.Even slight changes in the initial precipitation field can have a significant impact on the future precipitation patterns,making the nowcasting of short-term high-resolution precipitation a major challenge.Traditional deep learning methods often have difficulty capturing the long-term spatial dependence of precipitation and are usually at a low resolution.To address these issues,based upon the Simpler yet Better Video Prediction(SimVP)framework,we proposed a deep generative neural network that incorporates the Simple Parameter-Free Attention Module(SimAM)and Generative Adversarial Networks(GANs)for short-term high-resolution precipitation event forecasting.Through an adversarial training strategy,critical precipitation features were extracted from complex radar echo images.During the adversarial learning process,the dynamic competition between the generator and the discriminator could continuously enhance the model in prediction accuracy and resolution for short-term precipitation.Experimental results demonstrate that the proposed method could effectively forecast short-term precipitation events on various scales and showed the best overall performance among existing methods.
基金supported by the National Natural Science Foundation of China(Nos.62373215,62373219 and 62073193)the Natural Science Foundation of Shandong Province(No.ZR2023MF100)+1 种基金the Key Projects of the Ministry of Industry and Information Technology(No.TC220H057-2022)the Independently Developed Instrument Funds of Shandong University(No.zy20240201)。
文摘Current you only look once(YOLO)-based algorithm model is facing the challenge of overwhelming parameters and calculation complexity under the printed circuit board(PCB)defect detection application scenario.In order to solve this problem,we propose a new method,which combined the lightweight network mobile vision transformer(Mobile Vi T)with the convolutional block attention module(CBAM)mechanism and the new regression loss function.This method needed less computation resources,making it more suitable for embedded edge detection devices.Meanwhile,the new loss function improved the positioning accuracy of the bounding box and enhanced the robustness of the model.In addition,experiments on public datasets demonstrate that the improved model achieves an average accuracy of 87.9%across six typical defect detection tasks,while reducing computational costs by nearly 90%.It significantly reduces the model's computational requirements while maintaining accuracy,ensuring reliable performance for edge deployment.
基金supported by the Shanxi Agricultural University Science and Technology Innovation Enhancement Project。
文摘This paper proposes a lightweight traffic sign detection system based on you only look once(YOLO).Firstly,the classification to fusion(C2f)structure is integrated into the backbone network,employing deformable convolution and bi-directional feature pyramid network(BiFPN)_Concat to improve the adaptability of the network.Secondly,the simple attention module(SimAm)is embedded to prioritize key features and reduce the complexity of the model after the C2f layer at the end of the backbone network.Next,the focal efficient intersection over union(EloU)is introduced to adjust the weights of challenging samples.Finally,we accomplish the design and deployment for the mobile app.The results demonstrate improvements,with the F1 score of 0.8987,mean average precision(mAP)@0.5 of 98.8%,mAP@0.5:0.95 of 75.6%,and the detection speed of 50 frames per second(FPS).
基金supported by the Natural Science Foundation of Henan Province(Grant No.242300420297)awarded to Yi Sun.
文摘With the development of anti-virus technology,malicious documents have gradually become the main pathway of Advanced Persistent Threat(APT)attacks,therefore,the development of effective malicious document classifiers has become particularly urgent.Currently,detection methods based on document structure and behavioral features encounter challenges in feature engineering,these methods not only have limited accuracy,but also consume large resources,and usually can only detect documents in specific formats,which lacks versatility and adaptability.To address such problems,this paper proposes a novel malicious document detection method-visualizing documents as GGE images(Grayscale,Grayscale matrix,Entropy).The GGE method visualizes the original byte sequence of the malicious document as a grayscale image,the information entropy sequence of the document as an entropy image,and at the same time,the grayscale level co-occurrence matrix and the texture and spatial information stored in it are converted into grayscale matrix image,and fuses the three types of images to get the GGE color image.The Convolutional Block Attention Module-EfficientNet-B0(CBAM-EfficientNet-B0)model is then used for classification,combining transfer learning and applying the pre-trained model on the ImageNet dataset to the feature extraction process of GGE images.As shown in the experimental results,the GGE method has superior performance compared with other methods,which is suitable for detecting malicious documents in different formats,and achieves an accuracy of 99.44%and 97.39%on Portable Document Format(PDF)and office datasets,respectively,and consumes less time during the detection process,which can be effectively applied to the task of detecting malicious documents in real-time.
基金supported by the National Natural Science Foundation of China(No.61961037)the Industrial Support Plan of Education Department of Gansu Province(No.2021CYZC-30)。
文摘In order to solve the challenge of breast cancer region segmentation,we improved the U-Net.The convolutional block attention module with prioritized attention(CBAM-PA)and dilated transformer(Dformer)modules were designed to replace the convolutional layers at the encoding side in the base U-Net,the input logic of the U-Net was improved by dynamically adjusting the input size of each layer,and the short connections in the U-Net were replaced with crosslayer connections to enhance the image restoration capability at the decoding side.On the breast ultrasound images(BUSI)dataset,we obtain a Dice coefficient of 0.8031 and an intersection-over-union(IoU)value of 0.7362.The experimental results show that the proposed enhancement method effectively improves the accuracy and quality of breast cancer lesion region segmentation.
基金supported by the National Natural Science Foundation of China (Nos.61806107 and 61702135)。
文摘We propose a hierarchical multi-scale attention mechanism-based model in response to the low accuracy and inefficient manual classification of existing oceanic biological image classification methods. Firstly, the hierarchical efficient multi-scale attention(H-EMA) module is designed for lightweight feature extraction, achieving outstanding performance at a relatively low cost. Secondly, an improved EfficientNetV2 block is used to integrate information from different scales better and enhance inter-layer message passing. Furthermore, introducing the convolutional block attention module(CBAM) enhances the model's perception of critical features, optimizing its generalization ability. Lastly, Focal Loss is introduced to adjust the weights of complex samples to address the issue of imbalanced categories in the dataset, further improving the model's performance. The model achieved 96.11% accuracy on the intertidal marine organism dataset of Nanji Islands and 84.78% accuracy on the CIFAR-100 dataset, demonstrating its strong generalization ability to meet the demands of oceanic biological image classification.
基金supported by the Korea Electric Power Corporation(R22TA14,Development of Drone Systemfor Diagnosis of Porcelain Insulators in Overhead Transmission Lines)the National Fire Agency of Korea(RS-2024-00408270,Fire Hazard Analysis and Fire Safety Standards Development for Transportation and Storage Stage of Reuse Battery)the Ministry of the Interior and Safety of Korea(RS-2024-00408982,Development of Intelligent Fire Detection and Sprinkler Facility Technology Reflecting the Characteristics of Logistics Facilities).
文摘This paper proposes an automated detection framework for transmission facilities using a featureattention multi-scale robustness network(FAMSR-Net)with high-fidelity virtual images.The proposed framework exhibits three key characteristics.First,virtual images of the transmission facilities generated using StyleGAN2-ADA are co-trained with real images.This enables the neural network to learn various features of transmission facilities to improve the detection performance.Second,the convolutional block attention module is deployed in FAMSR-Net to effectively extract features from images and construct multi-dimensional feature maps,enabling the neural network to perform precise object detection in various environments.Third,an effective bounding box optimization method called Scylla-IoU is deployed on FAMSR-Net,considering the intersection over union,center point distance,angle,and shape of the bounding box.This enables the detection of power facilities of various sizes accurately.Extensive experiments demonstrated that FAMSRNet outperforms other neural networks in detecting power facilities.FAMSR-Net also achieved the highest detection accuracy when virtual images of the transmission facilities were co-trained in the training phase.The proposed framework is effective for the scheduled operation and maintenance of transmission facilities because an optical camera is currently the most promising tool for unmanned aerial vehicles.This ultimately contributes to improved inspection efficiency,reduced maintenance risks,and more reliable power delivery across extensive transmission facilities.
基金supported by the National Natural Science Foundation of China(Key Program)(No.11932013)the Tianjin Science and Technology Plan Project(No.22PTZWHZ00040)。
文摘With the rapid development of digital communication and the widespread use of the Internet of Things,multi-view image compression has attracted increasing attention as a fundamental technology for image data communication.Multi-view image compression aims to improve compression efficiency by leveraging correlations between images.However,the requirement of synchronization and inter-image communication at the encoder side poses significant challenges,especially for constrained devices.In this study,we introduce a novel distributed image compression model based on the attention mechanism to address the challenges associated with the availability of side information only during decoding.Our model integrates an encoder network,a quantization module,and a decoder network,to ensure both high compression performance and high-quality image reconstruction.The encoder uses a deep Convolutional Neural Network(CNN)to extract high-level features from the input image,which then pass through the quantization module for further compression before undergoing lossless entropy coding.The decoder of our model consists of three main components that allow us to fully exploit the information within and between images on the decoder side.Specifically,we first introduce a channel-spatial attention module to capture and refine information within individual image feature maps.Second,we employ a semi-coupled convolution module to extract both shared and specific information in images.Finally,a cross-attention module is employed to fuse mutual information extracted from side information.The effectiveness of our model is validated on various datasets,including KITTI Stereo and Cityscapes.The results highlight the superior compression capabilities of our method,surpassing state-of-the-art techniques.
基金funded by the National Natural Science Foundation of China(grant number:62172292).
文摘Vehicle re-identification involves matching images of vehicles across varying camera views.The diversity of camera locations along different roadways leads to significant intra-class variation and only minimal inter-class similarity in the collected vehicle images,which increases the complexity of re-identification tasks.To tackle these challenges,this study proposes AG-GCN(Attention-Guided Graph Convolutional Network),a novel framework integrating several pivotal components.Initially,AG-GCN embeds a lightweight attention module within the ResNet-50 structure to learn feature weights automatically,thereby improving the representation of vehicle features globally by highlighting salient features and suppressing extraneous ones.Moreover,AG-GCN adopts a graph-based structure to encapsulate deep local features.A graph convolutional network then amalgamates these features to understand the relationships among vehicle-related characteristics.Subsequently,we amalgamate feature maps from both the attention and graph-based branches for a more comprehensive representation of vehicle features.The framework then gauges feature similarities and ranks them,thus enhancing the accuracy of vehicle re-identification.Comprehensive qualitative and quantitative analyses on two publicly available datasets verify the efficacy of AG-GCN in addressing intra-class and inter-class variability issues.
基金supported by the National Natural Science Foundation of China(52001340)the Henan Province Science and Technology Key Research Project(242102110332)the Henan Province Teaching Reform Project(2022SYJXLX087).
文摘To address the issues of slow diagnostic speed,low accuracy,and poor generalization performance in traditional rolling bearing fault diagnosis methods,we propose a rolling bearing fault diagnosis method based on Markov Transition Field(MTF)image encoding combined with a lightweight convolutional neural network that integrates a Convolutional Block Attention Module(CBAM-LCNN).Specifically,we first use the Markov Transition Field to convert the original one-dimensional vibration signals of rolling bearings into two-dimensional images.Then,we construct a lightweight convolutional neural network incorporating the convolutional attention module(CBAM-LCNN).Finally,the two-dimensional images obtained from MTF mapping are fed into the CBAM-LCNN network for image feature extraction and fault diagnosis.We validate the effectiveness of the proposed method on the bearing fault datasets from Guangdong University of Petrochemical Technology’s multi-stage centrifugal fan and Case Western Reserve University.Experimental results show that,compared to other advanced baseline methods,the proposed rolling bearing fault diagnosis method offers faster diagnostic speed and higher diagnostic accuracy.In addition,we conducted experiments on the Xi’an Jiaotong University rolling bearing dataset,achieving excellent results in bearing fault diagnosis.These results validate the strong generalization performance of the proposed method.The method presented in this paper not only effectively diagnoses faults in rolling bearings but also serves as a reference for fault diagnosis in other equipment.
基金funded by Zhejiang Basic Public Welfare Research Project,grant number LZY24E060001supported by Guangzhou Development Zone Science and Technology(2021GH10,2020GH10,2023GH02)+1 种基金the University of Macao(MYRG2022-00271-FST)the Science and Technology Development Fund(FDCT)of Macao(0032/2022/A).
文摘With the continuous development of artificial intelligence and machine learning techniques,there have been effective methods supporting the work of dermatologist in the field of skin cancer detection.However,object significant challenges have been presented in accurately segmenting melanomas in dermoscopic images due to the objects that could interfere human observations,such as bubbles and scales.To address these challenges,we propose a dual U-Net network framework for skin melanoma segmentation.In our proposed architecture,we introduce several innovative components that aim to enhance the performance and capabilities of the traditional U-Net.First,we establish a novel framework that links two simplified U-Nets,enabling more comprehensive information exchange and feature integration throughout the network.Second,after cascading the second U-Net,we introduce a skip connection between the decoder and encoder networks,and incorporate a modified receptive field block(MRFB),which is designed to capture multi-scale spatial information.Third,to further enhance the feature representation capabilities,we add a multi-path convolution block attention module(MCBAM)to the first two layers of the first U-Net encoding,and integrate a new squeeze-and-excitation(SE)mechanism with residual connections in the second U-Net.To illustrate the performance of our proposed model,we conducted comprehensive experiments on widely recognized skin datasets.On the ISIC-2017 dataset,the IoU value of our proposed model increased from 0.6406 to 0.6819 and the Dice coefficient increased from 0.7625 to 0.8023.On the ISIC-2018 dataset,the IoU value of proposed model also improved from 0.7138 to 0.7709,while the Dice coefficient increased from 0.8285 to 0.8665.Furthermore,the generalization experiments conducted on the jaw cyst dataset from Quzhou People’s Hospital further verified the outstanding segmentation performance of the proposed model.These findings collectively affirm the potential of our approach as a valuable tool in supporting clinical decision-making in the field of skin cancer detection,as well as advancing research in medical image analysis.
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 by Qingdao Huanghai University School-Level ScientificResearch Project(2023KJ14)Undergraduate Teaching Reform Research Project of Shandong Provincial Department of Education(M2022328)+1 种基金National Natural Science Foundation of China under Grant(42472324)Qingdao Postdoctoral Foundation under Grant(QDBSH202402049).
文摘Multimodal image fusion plays an important role in image analysis and applications.Multimodal medical image fusion helps to combine contrast features from two or more input imaging modalities to represent fused information in a single image.One of the critical clinical applications of medical image fusion is to fuse anatomical and functional modalities for rapid diagnosis of malignant tissues.This paper proposes a multimodal medical image fusion network(MMIF-Net)based on multiscale hybrid attention.The method first decomposes the original image to obtain the low-rank and significant parts.Then,to utilize the features at different scales,we add amultiscalemechanism that uses three filters of different sizes to extract the features in the encoded network.Also,a hybrid attention module is introduced to obtain more image details.Finally,the fused images are reconstructed by decoding the network.We conducted experiments with clinical images from brain computed tomography/magnetic resonance.The experimental results show that the multimodal medical image fusion network method based on multiscale hybrid attention works better than other advanced fusion methods.
基金funded by Liaoning Provincial Department of Education Project,Award number JYTMS20230418.
文摘Pest detection techniques are helpful in reducing the frequency and scale of pest outbreaks;however,their application in the actual agricultural production process is still challenging owing to the problems of interspecies similarity,multi-scale,and background complexity of pests.To address these problems,this study proposes an FD-YOLO pest target detection model.The FD-YOLO model uses a Fully Connected Feature Pyramid Network(FC-FPN)instead of a PANet in the neck,which can adaptively fuse multi-scale information so that the model can retain small-scale target features in the deep layer,enhance large-scale target features in the shallow layer,and enhance the multiplexing of effective features.A dual self-attention module(DSA)is then embedded in the C3 module of the neck,which captures the dependencies between the information in both spatial and channel dimensions,effectively enhancing global features.We selected 16 types of pests that widely damage field crops in the IP102 pest dataset,which were used as our dataset after data supplementation and enhancement.The experimental results showed that FD-YOLO’s mAP@0.5 improved by 6.8%compared to YOLOv5,reaching 82.6%and 19.1%–5%better than other state-of-the-art models.This method provides an effective new approach for detecting similar or multiscale pests in field crops.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(*MSIT)(No.2018R1A5A7059549).
文摘The generation of high-quality,realistic face generation has emerged as a key field of research in computer vision.This paper proposes a robust approach that combines a Super-Resolution Generative Adversarial Network(SRGAN)with a Pyramid Attention Module(PAM)to enhance the quality of deep face generation.The SRGAN framework is designed to improve the resolution of generated images,addressing common challenges such as blurriness and a lack of intricate details.The Pyramid Attention Module further complements the process by focusing on multi-scale feature extraction,enabling the network to capture finer details and complex facial features more effectively.The proposed method was trained and evaluated over 100 epochs on the CelebA dataset,demonstrating consistent improvements in image quality and a marked decrease in generator and discriminator losses,reflecting the model’s capacity to learn and synthesize high-quality images effectively,given adequate computational resources.Experimental outcome demonstrates that the SRGAN model with PAM module has outperformed,yielding an aggregate discriminator loss of 0.055 for real,0.043 for fake,and a generator loss of 10.58 after training for 100 epochs.The model has yielded an structural similarity index measure of 0.923,that has outperformed the other models that are considered in the current study for analysis.
基金supported by the Jiangsu Province IUR Cooperation Project (No.BY2021258)the Wuxi Science and Technology Development Fund Project (No.G20212028)。
文摘An improved cycle-consistent generative adversarial network(CycleGAN) method for defect data augmentation based on feature fusion and self attention residual module is proposed to address the insufficiency of defect sample data for light guide plate(LGP) in production,as well as the problem of minor defects.Two optimizations are made to the generator of CycleGAN:fusion of low resolution features obtained from partial up-sampling and down-sampling with high-resolution features,combination of self attention mechanism with residual network structure to replace the original residual module.Qualitative and quantitative experiments were conducted to compare different data augmentation methods,and the results show that the defect images of the LGP generated by the improved network were more realistic,and the accuracy of the you only look once version 5(YOLOv5) detection network for the LGP was improved by 5.6%,proving the effectiveness and accuracy of the proposed method.
基金the Key Project of Basic Research of Yunnan Province(No.202101AS070016)。
文摘In order to meet the requirements of accurate identification of surface defects on copper strip in industrial production,a detection model of surface defects based on machine vision,CSC-YOLO,is proposed.The model uses YOLOv4-tiny as the benchmark network.First,K-means clustering is introduced into the benchmark network to obtain anchor frames that match the self-built dataset.Second,a cross-region fusion module is introduced in the backbone network to solve the difficult target recognition problem by fusing contextual semantic information.Third,the spatial pyramid pooling-efficient channel attention network(SPP-E)module is introduced in the path aggregation network(PANet)to enhance the extraction of features.Fourth,to prevent the loss of channel information,a lightweight attention mechanism is introduced to improve the performance of the network.Finally,the performance of the model is improved by adding adjustment factors to correct the loss function for the dimensional characteristics of the surface defects.CSC-YOLO was tested on the self-built dataset of surface defects in copper strip,and the experimental results showed that the mAP of the model can reach 93.58%,which is a 3.37% improvement compared with the benchmark network,and FPS,although decreasing compared with the benchmark network,reached 104.CSC-YOLO takes into account the real-time requirements of copper strip production.The comparison experiments with Faster RCNN,SSD300,YOLOv3,YOLOv4,Resnet50-YOLOv4,YOLOv5s,YOLOv7,and other algorithms show that the algorithm obtains a faster computation speed while maintaining a higher detection accuracy.
基金This paper is partially supported by Open Fund for Jiangsu Key Laboratory of Advanced Manufacturing Technology(HGAMTL-1703)Guangxi Key Laboratory of Trusted Software(kx201901)+5 种基金Fundamental Research Funds for the Central Universities(CDLS-2020-03)Key Laboratory of Child Development and Learning Science(Southeast University),Ministry of EducationRoyal Society International Exchanges Cost Share Award,UK(RP202G0230)Medical Research Council Confidence in Concept Award,UK(MC_PC_17171)Hope Foundation for Cancer Research,UK(RM60G0680)British Heart Foundation Accelerator Award,UK.
文摘Aim: To diagnose COVID-19 more efficiently and more correctly, this study proposed a novel attention network forCOVID-19 (ANC). Methods: Two datasets were used in this study. An 18-way data augmentation was proposed toavoid overfitting. Then, convolutional block attention module (CBAM) was integrated to our model, the structureof which is fine-tuned. Finally, Grad-CAM was used to provide an explainable diagnosis. Results: The accuracyof our ANC methods on two datasets are 96.32% ± 1.06%, and 96.00% ± 1.03%, respectively. Conclusions: Thisproposed ANC method is superior to 9 state-of-the-art approaches.
