In order to address the challenges posed by complex background interference,high miss-detection rates of micro-scale defects,and limited model deployment efficiency in photovoltaic(PV)module defect detection,this pape...In order to address the challenges posed by complex background interference,high miss-detection rates of micro-scale defects,and limited model deployment efficiency in photovoltaic(PV)module defect detection,this paper proposes an efficient detection framework based on an improved YOLOv11 architecture.First,a Re-parameterized Convolution(RepConv)module is integrated into the backbone to enhance the model’s sensitivity to fine-grained defects—such as micro-cracks and hot spots—while maintaining high inference efficiency.Second,a Multi-Scale Feature Fusion Convolutional Block Attention Mechanism(MSFF-CBAM)is designed to guide the network toward critical defect regions by jointly modeling channel-wise and spatial attention.This mechanism effectively strengthens the specificity and robustness of feature representations.Third,a lightweight Dynamic Sampling Module(DySample)is employed to replace conventional upsampling operations,thereby improving the localization accuracy of small-scale defect targets.Experimental evaluations conducted on the PVEL-AD dataset demonstrate that the proposed RMDYOLOv11 model surpasses the baseline YOLOv11 in terms of mean Average Precision(mAP)@0.5,Precision,and Recall,achieving respective improvements of 4.70%,1.51%,and 5.50%.The model also exhibits notable advantages in inference speed and model compactness.Further validation on the ELPV dataset confirms the model’s generalization capability,showing respective performance gains of 1.99%,2.28%,and 1.45%across the same metrics.Overall,the enhanced model significantly improves the accuracy of micro-defect identification on PV module surfaces,effectively reducing both false negatives and false positives.This advancement provides a robust and reliable technical foundation for automated PV module defect detection.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
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
Deep learning technology is widely used in computer vision.Generally,a large amount of data is used to train the model weights in deep learning,so as to obtain a model with higher accuracy.However,massive data and com...Deep learning technology is widely used in computer vision.Generally,a large amount of data is used to train the model weights in deep learning,so as to obtain a model with higher accuracy.However,massive data and complex model structures require more calculating resources.Since people generally can only carry and use mobile and portable devices in application scenarios,neural networks have limitations in terms of calculating resources,size and power consumption.Therefore,the efficient lightweight model MobileNet is used as the basic network in this study for optimization.First,the accuracy of the MobileNet model is improved by adding methods such as the convolutional block attention module(CBAM)and expansion convolution.Then,the MobileNet model is compressed by using pruning and weight quantization algorithms based on weight size.Afterwards,methods such as Python crawlers and data augmentation are employed to create a garbage classification data set.Based on the above model optimization strategy,the garbage classification mobile terminal application is deployed on mobile phones and raspberry pies,realizing completing the garbage classification task more conveniently.展开更多
The infrastructure and construction of roads are crucial for the economic and social development of a region,but traffic-related challenges like accidents and congestion persist.Artificial Intelligence(AI)and Machine ...The infrastructure and construction of roads are crucial for the economic and social development of a region,but traffic-related challenges like accidents and congestion persist.Artificial Intelligence(AI)and Machine Learning(ML)have been used in road infrastructure and construction,particularly with the Internet of Things(IoT)devices.Object detection in Computer Vision also plays a key role in improving road infrastructure and addressing trafficrelated problems.This study aims to use You Only Look Once version 7(YOLOv7),Convolutional Block Attention Module(CBAM),the most optimized object-detection algorithm,to detect and identify traffic signs,and analyze effective combinations of adaptive optimizers like Adaptive Moment estimation(Adam),Root Mean Squared Propagation(RMSprop)and Stochastic Gradient Descent(SGD)with the YOLOv7.Using a portion of German traffic signs for training,the study investigates the feasibility of adopting smaller datasets while maintaining high accuracy.The model proposed in this study not only improves traffic safety by detecting traffic signs but also has the potential to contribute to the rapid development of autonomous vehicle systems.The study results showed an impressive accuracy of 99.7%when using a batch size of 8 and the Adam optimizer.This high level of accuracy demonstrates the effectiveness of the proposed model for the image classification task of traffic sign recognition.展开更多
Existing explanation methods for Convolutional Neural Networks(CNNs)lack the pixel-level visualization explanations to generate the reliable fine-grained decision features.Since there are inconsistencies between the e...Existing explanation methods for Convolutional Neural Networks(CNNs)lack the pixel-level visualization explanations to generate the reliable fine-grained decision features.Since there are inconsistencies between the explanation and the actual behavior of the model to be interpreted,we propose a Fine-Grained Visual Explanation for CNN,namely F-GVE,which produces a fine-grained explanation with higher consistency to the decision of the original model.The exact backward class-specific gradients with respect to the input image is obtained to highlight the object-related pixels the model used to make prediction.In addition,for better visualization and less noise,F-GVE selects an appropriate threshold to filter the gradient during the calculation and the explanation map is obtained by element-wise multiplying the gradient and the input image to show fine-grained classification decision features.Experimental results demonstrate that F-GVE has good visual performances and highlights the importance of fine-grained decision features.Moreover,the faithfulness of the explanation in this paper is high and it is effective and practical on troubleshooting and debugging detection.展开更多
Pneumonia is part of the main diseases causing the death of children.It is generally diagnosed through chest Xray images.With the development of Deep Learning(DL),the diagnosis of pneumonia based on DL has received ex...Pneumonia is part of the main diseases causing the death of children.It is generally diagnosed through chest Xray images.With the development of Deep Learning(DL),the diagnosis of pneumonia based on DL has received extensive attention.However,due to the small difference between pneumonia and normal images,the performance of DL methods could be improved.This research proposes a new fine-grained Convolutional Neural Network(CNN)for children’s pneumonia diagnosis(FG-CPD).Firstly,the fine-grainedCNNclassificationwhich can handle the slight difference in images is investigated.To obtain the raw images from the real-world chest X-ray data,the YOLOv4 algorithm is trained to detect and position the chest part in the raw images.Secondly,a novel attention network is proposed,named SGNet,which integrates the spatial information and channel information of the images to locate the discriminative parts in the chest image for expanding the difference between pneumonia and normal images.Thirdly,the automatic data augmentation method is adopted to increase the diversity of the images and avoid the overfitting of FG-CPD.The FG-CPD has been tested on the public Chest X-ray 2017 dataset,and the results show that it has achieved great effect.Then,the FG-CPD is tested on the real chest X-ray images from children aged 3–12 years ago from Tongji Hospital.The results show that FG-CPD has achieved up to 96.91%accuracy,which can validate the potential of the FG-CPD.展开更多
Automatic modulation classification(AMC)aims at identifying the modulation of the received signals,which is a significant approach to identifying the target in military and civil applications.In this paper,a novel dat...Automatic modulation classification(AMC)aims at identifying the modulation of the received signals,which is a significant approach to identifying the target in military and civil applications.In this paper,a novel data-driven framework named convolutional and transformer-based deep neural network(CTDNN)is proposed to improve the classification performance.CTDNN can be divided into four modules,i.e.,convolutional neural network(CNN)backbone,transition module,transformer module,and final classifier.In the CNN backbone,a wide and deep convolution structure is designed,which consists of 1×15 convolution kernels and intensive cross-layer connections instead of traditional 1×3 kernels and sequential connections.In the transition module,a 1×1 convolution layer is utilized to compress the channels of the previous multi-scale CNN features.In the transformer module,three self-attention layers are designed for extracting global features and generating the classification vector.In the classifier,the final decision is made based on the maximum a posterior probability.Extensive simulations are conducted,and the result shows that our proposed CTDNN can achieve superior classification performance than traditional deep models.展开更多
Joint Multimodal Aspect-based Sentiment Analysis(JMASA)is a significant task in the research of multimodal fine-grained sentiment analysis,which combines two subtasks:Multimodal Aspect Term Extraction(MATE)and Multimo...Joint Multimodal Aspect-based Sentiment Analysis(JMASA)is a significant task in the research of multimodal fine-grained sentiment analysis,which combines two subtasks:Multimodal Aspect Term Extraction(MATE)and Multimodal Aspect-oriented Sentiment Classification(MASC).Currently,most existing models for JMASA only perform text and image feature encoding from a basic level,but often neglect the in-depth analysis of unimodal intrinsic features,which may lead to the low accuracy of aspect term extraction and the poor ability of sentiment prediction due to the insufficient learning of intra-modal features.Given this problem,we propose a Text-Image Feature Fine-grained Learning(TIFFL)model for JMASA.First,we construct an enhanced adjacency matrix of word dependencies and adopt graph convolutional network to learn the syntactic structure features for text,which addresses the context interference problem of identifying different aspect terms.Then,the adjective-noun pairs extracted from image are introduced to enable the semantic representation of visual features more intuitive,which addresses the ambiguous semantic extraction problem during image feature learning.Thereby,the model performance of aspect term extraction and sentiment polarity prediction can be further optimized and enhanced.Experiments on two Twitter benchmark datasets demonstrate that TIFFL achieves competitive results for JMASA,MATE and MASC,thus validating the effectiveness of our proposed methods.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
In this paper, we first give a sufficient and necessary condition for a Hopf algebra to be a Yetter-Drinfel'd module, and prove that the finite dual of a Yetter-Drinfel'd module is still a Yetter-Drinfel'd...In this paper, we first give a sufficient and necessary condition for a Hopf algebra to be a Yetter-Drinfel'd module, and prove that the finite dual of a Yetter-Drinfel'd module is still a Yetter-Drinfel'd module. Finally, we introduce a concept of convolution module.展开更多
The deep learning technology has shown impressive performance in various vision tasks such as image classification, object detection and semantic segmentation. In particular, recent advances of deep learning technique...The deep learning technology has shown impressive performance in various vision tasks such as image classification, object detection and semantic segmentation. In particular, recent advances of deep learning techniques bring encouraging performance to fine-grained image classification which aims to distinguish subordinate-level categories, such as bird species or dog breeds. This task is extremely challenging due to high intra-class and low inter-class variance. In this paper, we review four types of deep learning based fine-grained image classification approaches, including the general convolutional neural networks （CNNs）, part detection based, ensemble of networks based and visual attention based fine-grained image classification approaches. Besides, the deep learning based semantic segmentation approaches are also covered in this paper. The region proposal based and fully convolutional networks based approaches for semantic segmentation are introduced respectively.展开更多
Mining more discriminative temporal features to enrich temporal context representation is considered the key to fine-grained action recog-nition.Previous action recognition methods utilize a fixed spatiotemporal windo...Mining more discriminative temporal features to enrich temporal context representation is considered the key to fine-grained action recog-nition.Previous action recognition methods utilize a fixed spatiotemporal window to learn local video representation.However,these methods failed to capture complex motion patterns due to their limited receptive field.To solve the above problems,this paper proposes a lightweight Temporal Pyramid Excitation(TPE)module to capture the short,medium,and long-term temporal context.In this method,Temporal Pyramid(TP)module can effectively expand the temporal receptive field of the network by using the multi-temporal kernel decomposition without significantly increasing the computational cost.In addition,the Multi Excitation module can emphasize temporal importance to enhance the temporal feature representation learning.TPE can be integrated into ResNet50,and building a compact video learning framework-TPENet.Extensive validation experiments on several challenging benchmark(Something-Something V1,Something-Something V2,UCF-101,and HMDB51)datasets demonstrate that our method achieves a preferable balance between computation and accuracy.展开更多
Fine-grained image search is one of the most challenging tasks in computer vision that aims to retrieve similar images at the fine-grained level for a given query image.The key objective is to learn discriminative fin...Fine-grained image search is one of the most challenging tasks in computer vision that aims to retrieve similar images at the fine-grained level for a given query image.The key objective is to learn discriminative fine-grained features by training deep models such that similar images are clustered,and dissimilar images are separated in the low embedding space.Previous works primarily focused on defining local structure loss functions like triplet loss,pairwise loss,etc.However,training via these approaches takes a long training time,and they have poor accuracy.Additionally,representations learned through it tend to tighten up in the embedded space and lose generalizability to unseen classes.This paper proposes a noise-assisted representation learning method for fine-grained image retrieval to mitigate these issues.In the proposed work,class manifold learning is performed in which positive pairs are created with noise insertion operation instead of tightening class clusters.And other instances are treated as negatives within the same cluster.Then a loss function is defined to penalize when the distance between instances of the same class becomes too small relative to the noise pair in that class in embedded space.The proposed approach is validated on CARS-196 and CUB-200 datasets and achieved better retrieval results(85.38%recall@1 for CARS-196%and 70.13%recall@1 for CUB-200)compared to other existing methods.展开更多
Deep learning has achieved excellent results in various tasks in the field of computer vision,especially in fine-grained visual categorization.It aims to distinguish the subordinate categories of the label-level categ...Deep learning has achieved excellent results in various tasks in the field of computer vision,especially in fine-grained visual categorization.It aims to distinguish the subordinate categories of the label-level categories.Due to high intra-class variances and high inter-class similarity,the fine-grained visual categorization is extremely challenging.This paper first briefly introduces and analyzes the related public datasets.After that,some of the latest methods are reviewed.Based on the feature types,the feature processing methods,and the overall structure used in the model,we divide them into three types of methods:methods based on general convolutional neural network(CNN)and strong supervision of parts,methods based on single feature processing,and meth-ods based on multiple feature processing.Most methods of the first type have a relatively simple structure,which is the result of the initial research.The methods of the other two types include models that have special structures and training processes,which are helpful to obtain discriminative features.We conduct a specific analysis on several methods with high accuracy on pub-lic datasets.In addition,we support that the focus of the future research is to solve the demand of existing methods for the large amount of the data and the computing power.In terms of tech-nology,the extraction of the subtle feature information with the burgeoning vision transformer(ViT)network is also an important research direction.展开更多
Accurate vehicle detection is essential for autonomous driving,traffic monitoring,and intelligent transportation systems.This paper presents an enhanced YOLOv8n model that incorporates the Ghost Module,Convolutional B...Accurate vehicle detection is essential for autonomous driving,traffic monitoring,and intelligent transportation systems.This paper presents an enhanced YOLOv8n model that incorporates the Ghost Module,Convolutional Block Attention Module(CBAM),and Deformable Convolutional Networks v2(DCNv2).The Ghost Module streamlines feature generation to reduce redundancy,CBAM applies channel and spatial attention to improve feature focus,and DCNv2 enables adaptability to geometric variations in vehicle shapes.These components work together to improve both accuracy and computational efficiency.Evaluated on the KITTI dataset,the proposed model achieves 95.4%mAP@0.5—an 8.97% gain over standard YOLOv8n—along with 96.2% precision,93.7% recall,and a 94.93%F1-score.Comparative analysis with seven state-of-the-art detectors demonstrates consistent superiority in key performance metrics.An ablation study is also conducted to quantify the individual and combined contributions of GhostModule,CBAM,and DCNv2,highlighting their effectiveness in improving detection performance.By addressing feature redundancy,attention refinement,and spatial adaptability,the proposed model offers a robust and scalable solution for vehicle detection across diverse traffic scenarios.展开更多
The utilization of millimeter-wave frequencies and cognitive radio(CR)are promising ways to increase the spectral efficiency of wireless communication systems.However,conventional CR spectrum sensing techniques entail...The utilization of millimeter-wave frequencies and cognitive radio(CR)are promising ways to increase the spectral efficiency of wireless communication systems.However,conventional CR spectrum sensing techniques entail sampling the received signal at a Nyquist rate,and they are not viable for wideband signals due to their high cost.This paper expounds on how sub-Nyquist sampling in conjunction with deep learning can be leveraged to remove this limitation.To this end,we propose a multi-task learning(MTL)framework using convolutional neural networks for the joint inference of the underlying narrowband signal number,their modulation scheme,and their location in a wideband spectrum.We demonstrate the effectiveness of the proposed framework for real-world millimeter-wave wideband signals collected by physical devices,exhibiting a 91.7% accuracy in the joint inference task when considering up to two narrowband signals over a wideband spectrum.Ultimately,the proposed data-driven approach enables on-the-fly wideband spectrum sensing,combining accuracy,and computational efficiency,which are indispensable for CR and opportunistic networking.展开更多
Neural network-based methods for intrapulse modulation recognition in radar signals have demonstrated significant improvements in classification accuracy.However,these approaches often rely on complex network structur...Neural network-based methods for intrapulse modulation recognition in radar signals have demonstrated significant improvements in classification accuracy.However,these approaches often rely on complex network structures,resulting in high computational resource requirements that limit their practical deployment in real-world settings.To address this issue,this paper proposes a bottleneck residual network with efficient soft-thresholding(BRN-EST)network,which integrates multiple lightweight design strategies and noise-reduction modules to maintain high recognition accuracy while significantly reducing computational complexity.Experimental results on the classical low-probability-of-intercept(LPI)radar signal dataset demonstrate that BRN-EST achieves comparable accuracy to state-of-the-art methods while reducing computational complexity by approximately 50%.展开更多
基金supported by the Gansu Provincial Department of Education Industry Support Plan Project(2025CYZC-018).
文摘In order to address the challenges posed by complex background interference,high miss-detection rates of micro-scale defects,and limited model deployment efficiency in photovoltaic(PV)module defect detection,this paper proposes an efficient detection framework based on an improved YOLOv11 architecture.First,a Re-parameterized Convolution(RepConv)module is integrated into the backbone to enhance the model’s sensitivity to fine-grained defects—such as micro-cracks and hot spots—while maintaining high inference efficiency.Second,a Multi-Scale Feature Fusion Convolutional Block Attention Mechanism(MSFF-CBAM)is designed to guide the network toward critical defect regions by jointly modeling channel-wise and spatial attention.This mechanism effectively strengthens the specificity and robustness of feature representations.Third,a lightweight Dynamic Sampling Module(DySample)is employed to replace conventional upsampling operations,thereby improving the localization accuracy of small-scale defect targets.Experimental evaluations conducted on the PVEL-AD dataset demonstrate that the proposed RMDYOLOv11 model surpasses the baseline YOLOv11 in terms of mean Average Precision(mAP)@0.5,Precision,and Recall,achieving respective improvements of 4.70%,1.51%,and 5.50%.The model also exhibits notable advantages in inference speed and model compactness.Further validation on the ELPV dataset confirms the model’s generalization capability,showing respective performance gains of 1.99%,2.28%,and 1.45%across the same metrics.Overall,the enhanced model significantly improves the accuracy of micro-defect identification on PV module surfaces,effectively reducing both false negatives and false positives.This advancement provides a robust and reliable technical foundation for automated PV module defect detection.
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.
文摘Deep learning technology is widely used in computer vision.Generally,a large amount of data is used to train the model weights in deep learning,so as to obtain a model with higher accuracy.However,massive data and complex model structures require more calculating resources.Since people generally can only carry and use mobile and portable devices in application scenarios,neural networks have limitations in terms of calculating resources,size and power consumption.Therefore,the efficient lightweight model MobileNet is used as the basic network in this study for optimization.First,the accuracy of the MobileNet model is improved by adding methods such as the convolutional block attention module(CBAM)and expansion convolution.Then,the MobileNet model is compressed by using pruning and weight quantization algorithms based on weight size.Afterwards,methods such as Python crawlers and data augmentation are employed to create a garbage classification data set.Based on the above model optimization strategy,the garbage classification mobile terminal application is deployed on mobile phones and raspberry pies,realizing completing the garbage classification task more conveniently.
文摘The infrastructure and construction of roads are crucial for the economic and social development of a region,but traffic-related challenges like accidents and congestion persist.Artificial Intelligence(AI)and Machine Learning(ML)have been used in road infrastructure and construction,particularly with the Internet of Things(IoT)devices.Object detection in Computer Vision also plays a key role in improving road infrastructure and addressing trafficrelated problems.This study aims to use You Only Look Once version 7(YOLOv7),Convolutional Block Attention Module(CBAM),the most optimized object-detection algorithm,to detect and identify traffic signs,and analyze effective combinations of adaptive optimizers like Adaptive Moment estimation(Adam),Root Mean Squared Propagation(RMSprop)and Stochastic Gradient Descent(SGD)with the YOLOv7.Using a portion of German traffic signs for training,the study investigates the feasibility of adopting smaller datasets while maintaining high accuracy.The model proposed in this study not only improves traffic safety by detecting traffic signs but also has the potential to contribute to the rapid development of autonomous vehicle systems.The study results showed an impressive accuracy of 99.7%when using a batch size of 8 and the Adam optimizer.This high level of accuracy demonstrates the effectiveness of the proposed model for the image classification task of traffic sign recognition.
基金This work was partially supported by Beijing Natural Science Foundation(No.4222038)by Open Research Project of the State Key Laboratory of Media Convergence and Communication(Communication University of China),by the National Key RD Program of China(No.2021YFF0307600)and by Fundamental Research Funds for the Central Universities.
文摘Existing explanation methods for Convolutional Neural Networks(CNNs)lack the pixel-level visualization explanations to generate the reliable fine-grained decision features.Since there are inconsistencies between the explanation and the actual behavior of the model to be interpreted,we propose a Fine-Grained Visual Explanation for CNN,namely F-GVE,which produces a fine-grained explanation with higher consistency to the decision of the original model.The exact backward class-specific gradients with respect to the input image is obtained to highlight the object-related pixels the model used to make prediction.In addition,for better visualization and less noise,F-GVE selects an appropriate threshold to filter the gradient during the calculation and the explanation map is obtained by element-wise multiplying the gradient and the input image to show fine-grained classification decision features.Experimental results demonstrate that F-GVE has good visual performances and highlights the importance of fine-grained decision features.Moreover,the faithfulness of the explanation in this paper is high and it is effective and practical on troubleshooting and debugging detection.
基金supported in part by the Natural Science Foundation of China(NSFC)underGrant No.51805192,Major Special Science and Technology Project of Hubei Province under Grant No.2020AEA009sponsored by the State Key Laboratory of Digital Manufacturing Equipment and Technology(DMET)of Huazhong University of Science and Technology(HUST)under Grant No.DMETKF2020029.
文摘Pneumonia is part of the main diseases causing the death of children.It is generally diagnosed through chest Xray images.With the development of Deep Learning(DL),the diagnosis of pneumonia based on DL has received extensive attention.However,due to the small difference between pneumonia and normal images,the performance of DL methods could be improved.This research proposes a new fine-grained Convolutional Neural Network(CNN)for children’s pneumonia diagnosis(FG-CPD).Firstly,the fine-grainedCNNclassificationwhich can handle the slight difference in images is investigated.To obtain the raw images from the real-world chest X-ray data,the YOLOv4 algorithm is trained to detect and position the chest part in the raw images.Secondly,a novel attention network is proposed,named SGNet,which integrates the spatial information and channel information of the images to locate the discriminative parts in the chest image for expanding the difference between pneumonia and normal images.Thirdly,the automatic data augmentation method is adopted to increase the diversity of the images and avoid the overfitting of FG-CPD.The FG-CPD has been tested on the public Chest X-ray 2017 dataset,and the results show that it has achieved great effect.Then,the FG-CPD is tested on the real chest X-ray images from children aged 3–12 years ago from Tongji Hospital.The results show that FG-CPD has achieved up to 96.91%accuracy,which can validate the potential of the FG-CPD.
基金supported in part by the National Natural Science Foundation of China under Grant(62171045,62201090)in part by the National Key Research and Development Program of China under Grants(2020YFB1807602,2019YFB1804404).
文摘Automatic modulation classification(AMC)aims at identifying the modulation of the received signals,which is a significant approach to identifying the target in military and civil applications.In this paper,a novel data-driven framework named convolutional and transformer-based deep neural network(CTDNN)is proposed to improve the classification performance.CTDNN can be divided into four modules,i.e.,convolutional neural network(CNN)backbone,transition module,transformer module,and final classifier.In the CNN backbone,a wide and deep convolution structure is designed,which consists of 1×15 convolution kernels and intensive cross-layer connections instead of traditional 1×3 kernels and sequential connections.In the transition module,a 1×1 convolution layer is utilized to compress the channels of the previous multi-scale CNN features.In the transformer module,three self-attention layers are designed for extracting global features and generating the classification vector.In the classifier,the final decision is made based on the maximum a posterior probability.Extensive simulations are conducted,and the result shows that our proposed CTDNN can achieve superior classification performance than traditional deep models.
基金supported by the Science and Technology Project of Henan Province(No.222102210081).
文摘Joint Multimodal Aspect-based Sentiment Analysis(JMASA)is a significant task in the research of multimodal fine-grained sentiment analysis,which combines two subtasks:Multimodal Aspect Term Extraction(MATE)and Multimodal Aspect-oriented Sentiment Classification(MASC).Currently,most existing models for JMASA only perform text and image feature encoding from a basic level,but often neglect the in-depth analysis of unimodal intrinsic features,which may lead to the low accuracy of aspect term extraction and the poor ability of sentiment prediction due to the insufficient learning of intra-modal features.Given this problem,we propose a Text-Image Feature Fine-grained Learning(TIFFL)model for JMASA.First,we construct an enhanced adjacency matrix of word dependencies and adopt graph convolutional network to learn the syntactic structure features for text,which addresses the context interference problem of identifying different aspect terms.Then,the adjective-noun pairs extracted from image are introduced to enable the semantic representation of visual features more intuitive,which addresses the ambiguous semantic extraction problem during image feature learning.Thereby,the model performance of aspect term extraction and sentiment polarity prediction can be further optimized and enhanced.Experiments on two Twitter benchmark datasets demonstrate that TIFFL achieves competitive results for JMASA,MATE and MASC,thus validating the effectiveness of our proposed methods.
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.
文摘In this paper, we first give a sufficient and necessary condition for a Hopf algebra to be a Yetter-Drinfel'd module, and prove that the finite dual of a Yetter-Drinfel'd module is still a Yetter-Drinfel'd module. Finally, we introduce a concept of convolution module.
基金supported by the National Natural Science Foundation of China(Nos.61373121 and 61328205)Program for Sichuan Provincial Science Fund for Distinguished Young Scholars(No.13QNJJ0149)+1 种基金the Fundamental Research Funds for the Central UniversitiesChina Scholarship Council(No.201507000032)
文摘The deep learning technology has shown impressive performance in various vision tasks such as image classification, object detection and semantic segmentation. In particular, recent advances of deep learning techniques bring encouraging performance to fine-grained image classification which aims to distinguish subordinate-level categories, such as bird species or dog breeds. This task is extremely challenging due to high intra-class and low inter-class variance. In this paper, we review four types of deep learning based fine-grained image classification approaches, including the general convolutional neural networks （CNNs）, part detection based, ensemble of networks based and visual attention based fine-grained image classification approaches. Besides, the deep learning based semantic segmentation approaches are also covered in this paper. The region proposal based and fully convolutional networks based approaches for semantic segmentation are introduced respectively.
基金supported by the research team of Xi’an Traffic Engineering Institute and the Young and middle-aged fund project of Xi’an Traffic Engineering Institute (2022KY-02).
文摘Mining more discriminative temporal features to enrich temporal context representation is considered the key to fine-grained action recog-nition.Previous action recognition methods utilize a fixed spatiotemporal window to learn local video representation.However,these methods failed to capture complex motion patterns due to their limited receptive field.To solve the above problems,this paper proposes a lightweight Temporal Pyramid Excitation(TPE)module to capture the short,medium,and long-term temporal context.In this method,Temporal Pyramid(TP)module can effectively expand the temporal receptive field of the network by using the multi-temporal kernel decomposition without significantly increasing the computational cost.In addition,the Multi Excitation module can emphasize temporal importance to enhance the temporal feature representation learning.TPE can be integrated into ResNet50,and building a compact video learning framework-TPENet.Extensive validation experiments on several challenging benchmark(Something-Something V1,Something-Something V2,UCF-101,and HMDB51)datasets demonstrate that our method achieves a preferable balance between computation and accuracy.
文摘Fine-grained image search is one of the most challenging tasks in computer vision that aims to retrieve similar images at the fine-grained level for a given query image.The key objective is to learn discriminative fine-grained features by training deep models such that similar images are clustered,and dissimilar images are separated in the low embedding space.Previous works primarily focused on defining local structure loss functions like triplet loss,pairwise loss,etc.However,training via these approaches takes a long training time,and they have poor accuracy.Additionally,representations learned through it tend to tighten up in the embedded space and lose generalizability to unseen classes.This paper proposes a noise-assisted representation learning method for fine-grained image retrieval to mitigate these issues.In the proposed work,class manifold learning is performed in which positive pairs are created with noise insertion operation instead of tightening class clusters.And other instances are treated as negatives within the same cluster.Then a loss function is defined to penalize when the distance between instances of the same class becomes too small relative to the noise pair in that class in embedded space.The proposed approach is validated on CARS-196 and CUB-200 datasets and achieved better retrieval results(85.38%recall@1 for CARS-196%and 70.13%recall@1 for CUB-200)compared to other existing methods.
基金supported by the National Natural Science Foundation of China(61571453,61806218).
文摘Deep learning has achieved excellent results in various tasks in the field of computer vision,especially in fine-grained visual categorization.It aims to distinguish the subordinate categories of the label-level categories.Due to high intra-class variances and high inter-class similarity,the fine-grained visual categorization is extremely challenging.This paper first briefly introduces and analyzes the related public datasets.After that,some of the latest methods are reviewed.Based on the feature types,the feature processing methods,and the overall structure used in the model,we divide them into three types of methods:methods based on general convolutional neural network(CNN)and strong supervision of parts,methods based on single feature processing,and meth-ods based on multiple feature processing.Most methods of the first type have a relatively simple structure,which is the result of the initial research.The methods of the other two types include models that have special structures and training processes,which are helpful to obtain discriminative features.We conduct a specific analysis on several methods with high accuracy on pub-lic datasets.In addition,we support that the focus of the future research is to solve the demand of existing methods for the large amount of the data and the computing power.In terms of tech-nology,the extraction of the subtle feature information with the burgeoning vision transformer(ViT)network is also an important research direction.
文摘Accurate vehicle detection is essential for autonomous driving,traffic monitoring,and intelligent transportation systems.This paper presents an enhanced YOLOv8n model that incorporates the Ghost Module,Convolutional Block Attention Module(CBAM),and Deformable Convolutional Networks v2(DCNv2).The Ghost Module streamlines feature generation to reduce redundancy,CBAM applies channel and spatial attention to improve feature focus,and DCNv2 enables adaptability to geometric variations in vehicle shapes.These components work together to improve both accuracy and computational efficiency.Evaluated on the KITTI dataset,the proposed model achieves 95.4%mAP@0.5—an 8.97% gain over standard YOLOv8n—along with 96.2% precision,93.7% recall,and a 94.93%F1-score.Comparative analysis with seven state-of-the-art detectors demonstrates consistent superiority in key performance metrics.An ablation study is also conducted to quantify the individual and combined contributions of GhostModule,CBAM,and DCNv2,highlighting their effectiveness in improving detection performance.By addressing feature redundancy,attention refinement,and spatial adaptability,the proposed model offers a robust and scalable solution for vehicle detection across diverse traffic scenarios.
文摘The utilization of millimeter-wave frequencies and cognitive radio(CR)are promising ways to increase the spectral efficiency of wireless communication systems.However,conventional CR spectrum sensing techniques entail sampling the received signal at a Nyquist rate,and they are not viable for wideband signals due to their high cost.This paper expounds on how sub-Nyquist sampling in conjunction with deep learning can be leveraged to remove this limitation.To this end,we propose a multi-task learning(MTL)framework using convolutional neural networks for the joint inference of the underlying narrowband signal number,their modulation scheme,and their location in a wideband spectrum.We demonstrate the effectiveness of the proposed framework for real-world millimeter-wave wideband signals collected by physical devices,exhibiting a 91.7% accuracy in the joint inference task when considering up to two narrowband signals over a wideband spectrum.Ultimately,the proposed data-driven approach enables on-the-fly wideband spectrum sensing,combining accuracy,and computational efficiency,which are indispensable for CR and opportunistic networking.
基金supported by the National Defense Pre-Research Foundation of China during the“14th Five-Year Plan”under Grant No.629010204.
文摘Neural network-based methods for intrapulse modulation recognition in radar signals have demonstrated significant improvements in classification accuracy.However,these approaches often rely on complex network structures,resulting in high computational resource requirements that limit their practical deployment in real-world settings.To address this issue,this paper proposes a bottleneck residual network with efficient soft-thresholding(BRN-EST)network,which integrates multiple lightweight design strategies and noise-reduction modules to maintain high recognition accuracy while significantly reducing computational complexity.Experimental results on the classical low-probability-of-intercept(LPI)radar signal dataset demonstrate that BRN-EST achieves comparable accuracy to state-of-the-art methods while reducing computational complexity by approximately 50%.
