Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware reso...Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware resources. To address this issue, the MobileNetV1 network was developed, which employs depthwise convolution to reduce network complexity. MobileNetV1 employs a stride of 2 in several convolutional layers to decrease the spatial resolution of feature maps, thereby lowering computational costs. However, this stride setting can lead to a loss of spatial information, particularly affecting the detection and representation of smaller objects or finer details in images. To maintain the trade-off between complexity and model performance, a lightweight convolutional neural network with hierarchical multi-scale feature fusion based on the MobileNetV1 network is proposed. The network consists of two main subnetworks. The first subnetwork uses a depthwise dilated separable convolution (DDSC) layer to learn imaging features with fewer parameters, which results in a lightweight and computationally inexpensive network. Furthermore, depthwise dilated convolution in DDSC layer effectively expands the field of view of filters, allowing them to incorporate a larger context. The second subnetwork is a hierarchical multi-scale feature fusion (HMFF) module that uses parallel multi-resolution branches architecture to process the input feature map in order to extract the multi-scale feature information of the input image. Experimental results on the CIFAR-10, Malaria, and KvasirV1 datasets demonstrate that the proposed method is efficient, reducing the network parameters and computational cost by 65.02% and 39.78%, respectively, while maintaining the network performance compared to the MobileNetV1 baseline.展开更多
Named entity recognition(NER)is an important part in knowledge extraction and one of the main tasks in constructing knowledge graphs.In today’s Chinese named entity recognition(CNER)task,the BERT-BiLSTM-CRF model is ...Named entity recognition(NER)is an important part in knowledge extraction and one of the main tasks in constructing knowledge graphs.In today’s Chinese named entity recognition(CNER)task,the BERT-BiLSTM-CRF model is widely used and often yields notable results.However,recognizing each entity with high accuracy remains challenging.Many entities do not appear as single words but as part of complex phrases,making it difficult to achieve accurate recognition using word embedding information alone because the intricate lexical structure often impacts the performance.To address this issue,we propose an improved Bidirectional Encoder Representations from Transformers(BERT)character word conditional random field(CRF)(BCWC)model.It incorporates a pre-trained word embedding model using the skip-gram with negative sampling(SGNS)method,alongside traditional BERT embeddings.By comparing datasets with different word segmentation tools,we obtain enhanced word embedding features for segmented data.These features are then processed using the multi-scale convolution and iterated dilated convolutional neural networks(IDCNNs)with varying expansion rates to capture features at multiple scales and extract diverse contextual information.Additionally,a multi-attention mechanism is employed to fuse word and character embeddings.Finally,CRFs are applied to learn sequence constraints and optimize entity label annotations.A series of experiments are conducted on three public datasets,demonstrating that the proposed method outperforms the recent advanced baselines.BCWC is capable to address the challenge of recognizing complex entities by combining character-level and word-level embedding information,thereby improving the accuracy of CNER.Such a model is potential to the applications of more precise knowledge extraction such as knowledge graph construction and information retrieval,particularly in domain-specific natural language processing tasks that require high entity recognition precision.展开更多
Nuclearmagnetic resonance imaging of breasts often presents complex backgrounds.Breast tumors exhibit varying sizes,uneven intensity,and indistinct boundaries.These characteristics can lead to challenges such as low a...Nuclearmagnetic resonance imaging of breasts often presents complex backgrounds.Breast tumors exhibit varying sizes,uneven intensity,and indistinct boundaries.These characteristics can lead to challenges such as low accuracy and incorrect segmentation during tumor segmentation.Thus,we propose a two-stage breast tumor segmentation method leveraging multi-scale features and boundary attention mechanisms.Initially,the breast region of interest is extracted to isolate the breast area from surrounding tissues and organs.Subsequently,we devise a fusion network incorporatingmulti-scale features and boundary attentionmechanisms for breast tumor segmentation.We incorporate multi-scale parallel dilated convolution modules into the network,enhancing its capability to segment tumors of various sizes through multi-scale convolution and novel fusion techniques.Additionally,attention and boundary detection modules are included to augment the network’s capacity to locate tumors by capturing nonlocal dependencies in both spatial and channel domains.Furthermore,a hybrid loss function with boundary weight is employed to address sample class imbalance issues and enhance the network’s boundary maintenance capability through additional loss.Themethod was evaluated using breast data from 207 patients at RuijinHospital,resulting in a 6.64%increase in Dice similarity coefficient compared to the benchmarkU-Net.Experimental results demonstrate the superiority of the method over other segmentation techniques,with fewer model parameters.展开更多
微表情检测旨在视频中定位幅度微弱、时间短暂的表情区间。其难点在于有效提取面部区域间的动态关联特征和多尺度时序特征,进而精准捕捉面部各区域微小动作之间的关联。针对这些问题,提出了一种融合自适应图注意力和多尺度可变空洞卷积...微表情检测旨在视频中定位幅度微弱、时间短暂的表情区间。其难点在于有效提取面部区域间的动态关联特征和多尺度时序特征,进而精准捕捉面部各区域微小动作之间的关联。针对这些问题,提出了一种融合自适应图注意力和多尺度可变空洞卷积的微表情检测网络(AG-DDNet)。通过引入参数可学习矩阵来实现键值对的特征变换,通过计算面部区域特征向量间的相似度得到动态邻接矩阵,并结合图注意力机制计算区域间权重系数,实现特征的动态融合;采用了多尺度可变空洞卷积模块,通过自适应池化与卷积组合的预测器生成动态感受野,从而实现多尺度的特征提取;引入基于Fisher信息矩阵的自然梯度优化机制,通过Fisher Adam优化器有效捕捉参数空间的几何结构信息,实现学习率的精确自适应调整,从而显著增强了模型对微表情和宏表情的协同检测能力。在微表情检测任务中,该算法与同类代表性算法相比,在CAS(ME)2数据集和SAMM Long Videos数据集上的性能分别提升了54.20%和20.11%。与最新算法相比,两个数据集上的提升幅度分别为38.43%和6.81%,有效证明了该方法在长视频微表情检测任务上的优越性能。展开更多
Data-driven deep learning modeling has been increasingly applied to quality prediction in complex chemical processes.However,the data show complex temporal features due to different residence times and strong coupling...Data-driven deep learning modeling has been increasingly applied to quality prediction in complex chemical processes.However,the data show complex temporal features due to different residence times and strong coupling relationships among chemical entities.This study proposes a multi-scale temporal feature extraction module to extract local dynamic temporal features across different time scales and combines it with long short-term memory(LSTM)networks to capture global temporal patterns,thereby taking full advantage of available data.In addition,variable-wise channel attention is integrated into the model to enhance attention on the essential parts of the feature maps and improve predictive performance.Furthermore,by analyzing the attention weights,the model quickly identifies the key variables that significantly affect the predictions.Finally,the model is applied to a real corn starch liquefaction process and achieves an accurate product quality prediction with an R^(2) value of 0.9392,which represents a 4%to 9%improvement over traditional models and demonstrates the superiority of the proposed approach.展开更多
For real-time classification of rock-masses in hard-rock tunnels,quick determination of the rock lithology on the tunnel face during construction is essential.Motivated by current breakthroughs in artificial intellige...For real-time classification of rock-masses in hard-rock tunnels,quick determination of the rock lithology on the tunnel face during construction is essential.Motivated by current breakthroughs in artificial intelligence technology in machine vision,a new automatic detection approach for classifying tunnel lithology based on tunnel face images was developed.The method benefits from residual learning for training a deep convolutional neural network(DCNN),and a multi-scale dilated convolutional attention block is proposed.The block with different dilation rates can provide various receptive fields,and thus it can extract multi-scale features.Moreover,the attention mechanism is utilized to select the salient features adaptively and further improve the performance of the model.In this study,an initial image data set made up of photographs of tunnel faces consisting of basalt,granite,siltstone,and tuff was first collected.After classifying and enhancing the training,validation,and testing data sets,a new image data set was generated.A comparison of the experimental findings demonstrated that the suggested approach outperforms previous classifiers in terms of various indicators,including accuracy,precision,recall,F1-score,and computing time.Finally,a visualization analysis was performed to explain the process of the network in the classification of tunnel lithology through feature extraction.Overall,this study demonstrates the potential of using artificial intelligence methods for in situ rock lithology classification utilizing geological images of the tunnel face.展开更多
The YOLOv5 algorithm is widely used in edge computing systems for object detection.However,the limited computing resources of embedded devices and the large model size of existing deep learning based methods increase ...The YOLOv5 algorithm is widely used in edge computing systems for object detection.However,the limited computing resources of embedded devices and the large model size of existing deep learning based methods increase the difficulty of real-time object detection on edge devices.To address this issue,we propose a smaller,less computationally intensive,and more accurate algorithm for object detection.Multi-scale Feature Fusion-YOLO(MFF-YOLO)is built on top of the YOLOv5s framework,but it contains substantial improvements to YOLOv5s.First,we design the MFF module to improve the feature propagation path in the feature pyramid,which further integrates the semantic information from different paths of feature layers.Then,a large convolution-kernel module is used in the bottleneck.The structure enlarges the receptive field and preserves shallow semantic information,which overcomes the performance limitation arising from uneven propagation in Feature Pyramid Networks(FPN).In addition,a multi-branch downsampling method based on depthwise separable convolutions and a bottleneck structure with deformable convolutions are designed to reduce the complexity of the backbone network and minimize the real-time performance loss caused by the increased model complexity.The experimental results on PASCAL VOC and MS COCO datasets show that,compared with YOLOv5s,MFF-YOLO reduces the number of parameters by 7%and the number of FLoating point Operations Per second(FLOPs)by 11.8%.The mAP@0.5 has improved by 3.7%and 5.5%,and the mAP@0.5:0.95 has improved by 6.5%and 6.2%,respetively.Furthermore,compared with YOLOv7-tiny,PP-YOLO-tiny,and other mainstream methods,MFF-YOLO has achieved better results on multiple indicators.展开更多
Flooding and heavy rainfall under extreme weather conditions pose significant challenges to target detection algorithms.Traditional methods often struggle to address issues such as image blurring,dynamic noise interfe...Flooding and heavy rainfall under extreme weather conditions pose significant challenges to target detection algorithms.Traditional methods often struggle to address issues such as image blurring,dynamic noise interference,and variations in target scale.Conventional neural network(CNN)-based target detection approaches face notable limitations in such adverse weather scenarios,primarily due to the fixed geometric sampling structures that hinder adaptability to complex backgrounds and dynamically changing object appearances.To address these challenges,this paper proposes an optimized YOLOv9 model incorporating an improved deformable convolutional network(DCN)enhanced with a multi-scale dilated attention(MSDA)mechanism.Specifically,the DCN module enhances themodel’s adaptability to target deformation and noise interference by adaptively adjusting the sampling grid positions,while also integrating feature amplitude modulation to further improve robustness.Additionally,theMSDA module is introduced to capture contextual features acrossmultiple scales,effectively addressing issues related to target occlusion and scale variation commonly encountered in flood-affected environments.Experimental evaluations are conducted on the ISE-UFDS and UA-DETRAC datasets.The results demonstrate that the proposedmodel significantly outperforms state-of-the-art methods in key evaluation metrics,including precision,recall,F1-score,and mAP(Mean Average Precision).Notably,the model exhibits superior robustness and generalization performance under simulated severe weather conditions,offering reliable technical support for disaster emergency response systems.This study contributes to enhancing the accuracy and real-time capabilities of flood early warning systems,thereby supporting more effective disaster mitigation strategies.展开更多
Retinal vessel segmentation in fundus images plays an essential role in the screening,diagnosis,and treatment of many diseases.The acquired fundus images generally have the following problems:uneven illumination,high ...Retinal vessel segmentation in fundus images plays an essential role in the screening,diagnosis,and treatment of many diseases.The acquired fundus images generally have the following problems:uneven illumination,high noise,and complex structure.It makes vessel segmentation very challenging.Previous methods of retinal vascular segmentation mainly use convolutional neural networks on U Network(U-Net)models,and they have many limitations and shortcomings,such as the loss of microvascular details at the end of the vessels.We address the limitations of convolution by introducing the transformer into retinal vessel segmentation.Therefore,we propose a hybrid method for retinal vessel segmentation based on modulated deformable convolution and the transformer,named DT-Net.Firstly,multi-scale image features are extracted by deformable convolution and multi-head selfattention(MHSA).Secondly,image information is recovered,and vessel morphology is refined by the proposed transformer decoder block.Finally,the local prediction results are obtained by the side output layer.The accuracy of the vessel segmentation is improved by the hybrid loss function.Experimental results show that our method obtains good segmentation performance on Specificity(SP),Sensitivity(SE),Accuracy(ACC),Curve(AUC),and F1-score on three publicly available fundus datasets such as DRIVE,STARE,and CHASE_DB1.展开更多
Background Document images such as statistical reports and scientific journals are widely used in information technology.Accurate detection of table areas in document images is an essential prerequisite for tasks such...Background Document images such as statistical reports and scientific journals are widely used in information technology.Accurate detection of table areas in document images is an essential prerequisite for tasks such as information extraction.However,because of the diversity in the shapes and sizes of tables,existing table detection methods adapted from general object detection algorithms,have not yet achieved satisfactory results.Incorrect detection results might lead to the loss of critical information.Methods Therefore,we propose a novel end-to-end trainable deep network combined with a self-supervised pretraining transformer for feature extraction to minimize incorrect detections.To better deal with table areas of different shapes and sizes,we added a dualbranch context content attention module(DCCAM)to high-dimensional features to extract context content information,thereby enhancing the network's ability to learn shape features.For feature fusion at different scales,we replaced the original 3×3 convolution with a multilayer residual module,which contains enhanced gradient flow information to improve the feature representation and extraction capability.Results We evaluated our method on public document datasets and compared it with previous methods,which achieved state-of-the-art results in terms of evaluation metrics such as recall and F1-score.https://github.com/Yong Z-Lee/TD-DCCAM.展开更多
Background Recurrent recovery is a common method for video super-resolution(VSR)that models the correlation between frames via hidden states.However,the application of this structure in real-world scenarios can lead t...Background Recurrent recovery is a common method for video super-resolution(VSR)that models the correlation between frames via hidden states.However,the application of this structure in real-world scenarios can lead to unsatisfactory artifacts.We found that in real-world VSR training,the use of unknown and complex degradation can better simulate the degradation process in the real world.Methods Based on this,we propose the RealFuVSR model,which simulates real-world degradation and mitigates artifacts caused by the VSR.Specifically,we propose a multiscale feature extraction module(MSF)module that extracts and fuses features from multiple scales,thereby facilitating the elimination of hidden state artifacts.To improve the accuracy of the hidden state alignment information,RealFuVSR uses an advanced optical flow-guided deformable convolution.Moreover,a cascaded residual upsampling module was used to eliminate noise caused by the upsampling process.Results The experiment demonstrates that RealFuVSR model can not only recover high-quality videos but also outperforms the state-of-the-art RealBasicVSR and RealESRGAN models.展开更多
文摘Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware resources. To address this issue, the MobileNetV1 network was developed, which employs depthwise convolution to reduce network complexity. MobileNetV1 employs a stride of 2 in several convolutional layers to decrease the spatial resolution of feature maps, thereby lowering computational costs. However, this stride setting can lead to a loss of spatial information, particularly affecting the detection and representation of smaller objects or finer details in images. To maintain the trade-off between complexity and model performance, a lightweight convolutional neural network with hierarchical multi-scale feature fusion based on the MobileNetV1 network is proposed. The network consists of two main subnetworks. The first subnetwork uses a depthwise dilated separable convolution (DDSC) layer to learn imaging features with fewer parameters, which results in a lightweight and computationally inexpensive network. Furthermore, depthwise dilated convolution in DDSC layer effectively expands the field of view of filters, allowing them to incorporate a larger context. The second subnetwork is a hierarchical multi-scale feature fusion (HMFF) module that uses parallel multi-resolution branches architecture to process the input feature map in order to extract the multi-scale feature information of the input image. Experimental results on the CIFAR-10, Malaria, and KvasirV1 datasets demonstrate that the proposed method is efficient, reducing the network parameters and computational cost by 65.02% and 39.78%, respectively, while maintaining the network performance compared to the MobileNetV1 baseline.
基金supported by the International Research Center of Big Data for Sustainable Development Goals under Grant No.CBAS2022GSP05the Open Fund of State Key Laboratory of Remote Sensing Science under Grant No.6142A01210404the Hubei Key Laboratory of Intelligent Geo-Information Processing under Grant No.KLIGIP-2022-B03.
文摘Named entity recognition(NER)is an important part in knowledge extraction and one of the main tasks in constructing knowledge graphs.In today’s Chinese named entity recognition(CNER)task,the BERT-BiLSTM-CRF model is widely used and often yields notable results.However,recognizing each entity with high accuracy remains challenging.Many entities do not appear as single words but as part of complex phrases,making it difficult to achieve accurate recognition using word embedding information alone because the intricate lexical structure often impacts the performance.To address this issue,we propose an improved Bidirectional Encoder Representations from Transformers(BERT)character word conditional random field(CRF)(BCWC)model.It incorporates a pre-trained word embedding model using the skip-gram with negative sampling(SGNS)method,alongside traditional BERT embeddings.By comparing datasets with different word segmentation tools,we obtain enhanced word embedding features for segmented data.These features are then processed using the multi-scale convolution and iterated dilated convolutional neural networks(IDCNNs)with varying expansion rates to capture features at multiple scales and extract diverse contextual information.Additionally,a multi-attention mechanism is employed to fuse word and character embeddings.Finally,CRFs are applied to learn sequence constraints and optimize entity label annotations.A series of experiments are conducted on three public datasets,demonstrating that the proposed method outperforms the recent advanced baselines.BCWC is capable to address the challenge of recognizing complex entities by combining character-level and word-level embedding information,thereby improving the accuracy of CNER.Such a model is potential to the applications of more precise knowledge extraction such as knowledge graph construction and information retrieval,particularly in domain-specific natural language processing tasks that require high entity recognition precision.
基金funded by the National Natural Foundation of China under Grant No.61172167the Science Fund Project of Heilongjiang Province(LH2020F035).
文摘Nuclearmagnetic resonance imaging of breasts often presents complex backgrounds.Breast tumors exhibit varying sizes,uneven intensity,and indistinct boundaries.These characteristics can lead to challenges such as low accuracy and incorrect segmentation during tumor segmentation.Thus,we propose a two-stage breast tumor segmentation method leveraging multi-scale features and boundary attention mechanisms.Initially,the breast region of interest is extracted to isolate the breast area from surrounding tissues and organs.Subsequently,we devise a fusion network incorporatingmulti-scale features and boundary attentionmechanisms for breast tumor segmentation.We incorporate multi-scale parallel dilated convolution modules into the network,enhancing its capability to segment tumors of various sizes through multi-scale convolution and novel fusion techniques.Additionally,attention and boundary detection modules are included to augment the network’s capacity to locate tumors by capturing nonlocal dependencies in both spatial and channel domains.Furthermore,a hybrid loss function with boundary weight is employed to address sample class imbalance issues and enhance the network’s boundary maintenance capability through additional loss.Themethod was evaluated using breast data from 207 patients at RuijinHospital,resulting in a 6.64%increase in Dice similarity coefficient compared to the benchmarkU-Net.Experimental results demonstrate the superiority of the method over other segmentation techniques,with fewer model parameters.
文摘微表情检测旨在视频中定位幅度微弱、时间短暂的表情区间。其难点在于有效提取面部区域间的动态关联特征和多尺度时序特征,进而精准捕捉面部各区域微小动作之间的关联。针对这些问题,提出了一种融合自适应图注意力和多尺度可变空洞卷积的微表情检测网络(AG-DDNet)。通过引入参数可学习矩阵来实现键值对的特征变换,通过计算面部区域特征向量间的相似度得到动态邻接矩阵,并结合图注意力机制计算区域间权重系数,实现特征的动态融合;采用了多尺度可变空洞卷积模块,通过自适应池化与卷积组合的预测器生成动态感受野,从而实现多尺度的特征提取;引入基于Fisher信息矩阵的自然梯度优化机制,通过Fisher Adam优化器有效捕捉参数空间的几何结构信息,实现学习率的精确自适应调整,从而显著增强了模型对微表情和宏表情的协同检测能力。在微表情检测任务中,该算法与同类代表性算法相比,在CAS(ME)2数据集和SAMM Long Videos数据集上的性能分别提升了54.20%和20.11%。与最新算法相比,两个数据集上的提升幅度分别为38.43%和6.81%,有效证明了该方法在长视频微表情检测任务上的优越性能。
基金the financial support provided by the Special Foundation for State Major Basic Research Program of China(2021YFD2101005)National Natural Science Foundation of China(22478057,22178045).
文摘Data-driven deep learning modeling has been increasingly applied to quality prediction in complex chemical processes.However,the data show complex temporal features due to different residence times and strong coupling relationships among chemical entities.This study proposes a multi-scale temporal feature extraction module to extract local dynamic temporal features across different time scales and combines it with long short-term memory(LSTM)networks to capture global temporal patterns,thereby taking full advantage of available data.In addition,variable-wise channel attention is integrated into the model to enhance attention on the essential parts of the feature maps and improve predictive performance.Furthermore,by analyzing the attention weights,the model quickly identifies the key variables that significantly affect the predictions.Finally,the model is applied to a real corn starch liquefaction process and achieves an accurate product quality prediction with an R^(2) value of 0.9392,which represents a 4%to 9%improvement over traditional models and demonstrates the superiority of the proposed approach.
基金funded by the National Natural Science Foundation of China(Grant No.51978460)the Open Fund of State Key Laboratory of Shield Machine and Boring Technology(No.SKLST-2019-K08).
文摘For real-time classification of rock-masses in hard-rock tunnels,quick determination of the rock lithology on the tunnel face during construction is essential.Motivated by current breakthroughs in artificial intelligence technology in machine vision,a new automatic detection approach for classifying tunnel lithology based on tunnel face images was developed.The method benefits from residual learning for training a deep convolutional neural network(DCNN),and a multi-scale dilated convolutional attention block is proposed.The block with different dilation rates can provide various receptive fields,and thus it can extract multi-scale features.Moreover,the attention mechanism is utilized to select the salient features adaptively and further improve the performance of the model.In this study,an initial image data set made up of photographs of tunnel faces consisting of basalt,granite,siltstone,and tuff was first collected.After classifying and enhancing the training,validation,and testing data sets,a new image data set was generated.A comparison of the experimental findings demonstrated that the suggested approach outperforms previous classifiers in terms of various indicators,including accuracy,precision,recall,F1-score,and computing time.Finally,a visualization analysis was performed to explain the process of the network in the classification of tunnel lithology through feature extraction.Overall,this study demonstrates the potential of using artificial intelligence methods for in situ rock lithology classification utilizing geological images of the tunnel face.
基金supported by the Natural Science Foundation of Shandong Province(Nos.ZR2023LZH017 and ZR2024MF066)the Natural Science Foundation of Hebei Province(No.F2022511001)+1 种基金the Key Funding from National Natural Science Foundation of China(No.92067206)the National Natural Science Foundation of China(No.62471493).
文摘The YOLOv5 algorithm is widely used in edge computing systems for object detection.However,the limited computing resources of embedded devices and the large model size of existing deep learning based methods increase the difficulty of real-time object detection on edge devices.To address this issue,we propose a smaller,less computationally intensive,and more accurate algorithm for object detection.Multi-scale Feature Fusion-YOLO(MFF-YOLO)is built on top of the YOLOv5s framework,but it contains substantial improvements to YOLOv5s.First,we design the MFF module to improve the feature propagation path in the feature pyramid,which further integrates the semantic information from different paths of feature layers.Then,a large convolution-kernel module is used in the bottleneck.The structure enlarges the receptive field and preserves shallow semantic information,which overcomes the performance limitation arising from uneven propagation in Feature Pyramid Networks(FPN).In addition,a multi-branch downsampling method based on depthwise separable convolutions and a bottleneck structure with deformable convolutions are designed to reduce the complexity of the backbone network and minimize the real-time performance loss caused by the increased model complexity.The experimental results on PASCAL VOC and MS COCO datasets show that,compared with YOLOv5s,MFF-YOLO reduces the number of parameters by 7%and the number of FLoating point Operations Per second(FLOPs)by 11.8%.The mAP@0.5 has improved by 3.7%and 5.5%,and the mAP@0.5:0.95 has improved by 6.5%and 6.2%,respetively.Furthermore,compared with YOLOv7-tiny,PP-YOLO-tiny,and other mainstream methods,MFF-YOLO has achieved better results on multiple indicators.
基金financially supported by the National Key R&D Program of China(No.2022YFC3090603)R&DProgramof BeijingMunicipal EducationCommission(No.KZ202211417049)。
文摘Flooding and heavy rainfall under extreme weather conditions pose significant challenges to target detection algorithms.Traditional methods often struggle to address issues such as image blurring,dynamic noise interference,and variations in target scale.Conventional neural network(CNN)-based target detection approaches face notable limitations in such adverse weather scenarios,primarily due to the fixed geometric sampling structures that hinder adaptability to complex backgrounds and dynamically changing object appearances.To address these challenges,this paper proposes an optimized YOLOv9 model incorporating an improved deformable convolutional network(DCN)enhanced with a multi-scale dilated attention(MSDA)mechanism.Specifically,the DCN module enhances themodel’s adaptability to target deformation and noise interference by adaptively adjusting the sampling grid positions,while also integrating feature amplitude modulation to further improve robustness.Additionally,theMSDA module is introduced to capture contextual features acrossmultiple scales,effectively addressing issues related to target occlusion and scale variation commonly encountered in flood-affected environments.Experimental evaluations are conducted on the ISE-UFDS and UA-DETRAC datasets.The results demonstrate that the proposedmodel significantly outperforms state-of-the-art methods in key evaluation metrics,including precision,recall,F1-score,and mAP(Mean Average Precision).Notably,the model exhibits superior robustness and generalization performance under simulated severe weather conditions,offering reliable technical support for disaster emergency response systems.This study contributes to enhancing the accuracy and real-time capabilities of flood early warning systems,thereby supporting more effective disaster mitigation strategies.
基金supported in part by the National Natural Science Foundation of China under Grant 61972267the National Natural Science Foundation of Hebei Province under Grant F2018210148the University Science Research Project of Hebei Province under Grant ZD2021334.
文摘Retinal vessel segmentation in fundus images plays an essential role in the screening,diagnosis,and treatment of many diseases.The acquired fundus images generally have the following problems:uneven illumination,high noise,and complex structure.It makes vessel segmentation very challenging.Previous methods of retinal vascular segmentation mainly use convolutional neural networks on U Network(U-Net)models,and they have many limitations and shortcomings,such as the loss of microvascular details at the end of the vessels.We address the limitations of convolution by introducing the transformer into retinal vessel segmentation.Therefore,we propose a hybrid method for retinal vessel segmentation based on modulated deformable convolution and the transformer,named DT-Net.Firstly,multi-scale image features are extracted by deformable convolution and multi-head selfattention(MHSA).Secondly,image information is recovered,and vessel morphology is refined by the proposed transformer decoder block.Finally,the local prediction results are obtained by the side output layer.The accuracy of the vessel segmentation is improved by the hybrid loss function.Experimental results show that our method obtains good segmentation performance on Specificity(SP),Sensitivity(SE),Accuracy(ACC),Curve(AUC),and F1-score on three publicly available fundus datasets such as DRIVE,STARE,and CHASE_DB1.
文摘Background Document images such as statistical reports and scientific journals are widely used in information technology.Accurate detection of table areas in document images is an essential prerequisite for tasks such as information extraction.However,because of the diversity in the shapes and sizes of tables,existing table detection methods adapted from general object detection algorithms,have not yet achieved satisfactory results.Incorrect detection results might lead to the loss of critical information.Methods Therefore,we propose a novel end-to-end trainable deep network combined with a self-supervised pretraining transformer for feature extraction to minimize incorrect detections.To better deal with table areas of different shapes and sizes,we added a dualbranch context content attention module(DCCAM)to high-dimensional features to extract context content information,thereby enhancing the network's ability to learn shape features.For feature fusion at different scales,we replaced the original 3×3 convolution with a multilayer residual module,which contains enhanced gradient flow information to improve the feature representation and extraction capability.Results We evaluated our method on public document datasets and compared it with previous methods,which achieved state-of-the-art results in terms of evaluation metrics such as recall and F1-score.https://github.com/Yong Z-Lee/TD-DCCAM.
基金Supported by Open Project of the Ministry of Industry and Information Technology Key Laboratory of Performance and Reliability Testing and Evaluation for Basic Software and Hardware。
文摘Background Recurrent recovery is a common method for video super-resolution(VSR)that models the correlation between frames via hidden states.However,the application of this structure in real-world scenarios can lead to unsatisfactory artifacts.We found that in real-world VSR training,the use of unknown and complex degradation can better simulate the degradation process in the real world.Methods Based on this,we propose the RealFuVSR model,which simulates real-world degradation and mitigates artifacts caused by the VSR.Specifically,we propose a multiscale feature extraction module(MSF)module that extracts and fuses features from multiple scales,thereby facilitating the elimination of hidden state artifacts.To improve the accuracy of the hidden state alignment information,RealFuVSR uses an advanced optical flow-guided deformable convolution.Moreover,a cascaded residual upsampling module was used to eliminate noise caused by the upsampling process.Results The experiment demonstrates that RealFuVSR model can not only recover high-quality videos but also outperforms the state-of-the-art RealBasicVSR and RealESRGAN models.
