In this paper we discuss policy iteration methods for approximate solution of a finite-state discounted Markov decision problem, with a focus on feature-based aggregation methods and their connection with deep reinfor...In this paper we discuss policy iteration methods for approximate solution of a finite-state discounted Markov decision problem, with a focus on feature-based aggregation methods and their connection with deep reinforcement learning schemes. We introduce features of the states of the original problem, and we formulate a smaller "aggregate" Markov decision problem, whose states relate to the features. We discuss properties and possible implementations of this type of aggregation, including a new approach to approximate policy iteration. In this approach the policy improvement operation combines feature-based aggregation with feature construction using deep neural networks or other calculations. We argue that the cost function of a policy may be approximated much more accurately by the nonlinear function of the features provided by aggregation, than by the linear function of the features provided by neural networkbased reinforcement learning, thereby potentially leading to more effective policy improvement.展开更多
Aiming at the problem of low detection accuracy due to the different scale sizes of apple leaf disease spots and their similarity to the background,this paper proposes a multi-scale lightweight network(MSL-Net).Firstl...Aiming at the problem of low detection accuracy due to the different scale sizes of apple leaf disease spots and their similarity to the background,this paper proposes a multi-scale lightweight network(MSL-Net).Firstly,a multiplexed aggregated feature extraction network is proposed using residual bottleneck block(RES-Bottleneck)and middle partial-convolution(MP-Conv)to capture multi-scale spatial features and enhance focus on disease features for better differentiation between disease targets and background information.Secondly,a lightweight feature fusion network is designed using scale-fuse concatenation(SF-Cat)and triple-scale sequence feature fusion(TSSF)module to merge multi-scale feature maps comprehensively.Depthwise convolution(DWConv)and GhostNet lighten the network,while the cross stage partial bottleneck with 3 convolutions ghost-normalization attention module(C3-GN)reduces missed detections by suppressing irrelevant background information.Finally,soft non-maximum suppression(Soft-NMS)is used in the post-processing stage to improve the problem of misdetection of dense disease sites.The results show that the MSL-Net improves mean average precision at intersection over union of 0.5(mAP@0.5)by 2.0%over the baseline you only look once version 5s(YOLOv5s)and reduces parameters by 44%,reducing computation by 27%,outperforming other state-of-the-art(SOTA)models overall.This method also shows excellent performance compared to the latest research.展开更多
Classroom behavior recognition is a hot research topic,which plays a vital role in assessing and improving the quality of classroom teaching.However,existing classroom behavior recognition methods have challenges for ...Classroom behavior recognition is a hot research topic,which plays a vital role in assessing and improving the quality of classroom teaching.However,existing classroom behavior recognition methods have challenges for high recognition accuracy with datasets with problems such as scenes with blurred pictures,and inconsistent objects.To address this challenge,we proposed an effective,lightweight object detector method called the RFNet model(YOLO-FR).The YOLO-FR is a lightweight and effective model.Specifically,for efficient multi-scale feature extraction,effective feature pyramid shared convolutional(FPSC)was designed to improve the feature extract performance by leveraging convolutional layers with varying dilation rates from the input image in the backbone.Secondly,to address the problem of multi-scale variability in the scene,we design the Rep Ghost fusion Cross Stage Partial and Efficient Layer Aggregation Network(RGCSPELAN)to improve the network performance further and reduce the amount of computation and the number of parameters.In addition,by conducting experimental valuation on the SCB dataset3 and STBD-08 dataset.Experimental results indicate that,compared to the baseline model,the RFNet model has increased mean accuracy precision(mAP@50)from 69.6%to 71.0%on the SCB dataset3 and from 91.8%to 93.1%on the STBD-08 dataset.The RFNet approach has effectiveness precision at 68.6%,surpassing the baseline method(YOLOv11)at 3.3%and archieve the minimal size(4.9 M)on the SCB dataset3.Finally,comparing it with other algorithms,it accurately detects student behavior in complex classroom environments results confirmed that RFNet is well-suited for real-time and efficiently recognizing classroom behaviors.展开更多
The number of blogs and other forms of opinionated online content has increased dramatically in recent years.Many fields,including academia and national security,place an emphasis on automated political article orient...The number of blogs and other forms of opinionated online content has increased dramatically in recent years.Many fields,including academia and national security,place an emphasis on automated political article orientation detection.Political articles(especially in the Arab world)are different from other articles due to their subjectivity,in which the author’s beliefs and political affiliation might have a significant influence on a political article.With categories representing the main political ideologies,this problem may be thought of as a subset of the text categorization(classification).In general,the performance of machine learning models for text classification is sensitive to hyperparameter settings.Furthermore,the feature vector used to represent a document must capture,to some extent,the complex semantics of natural language.To this end,this paper presents an intelligent system to detect political Arabic article orientation that adapts the categorical boosting(CatBoost)method combined with a multi-level feature concept.Extracting features at multiple levels can enhance the model’s ability to discriminate between different classes or patterns.Each level may capture different aspects of the input data,contributing to a more comprehensive representation.CatBoost,a robust and efficient gradient-boosting algorithm,is utilized to effectively learn and predict the complex relationships between these features and the political orientation labels associated with the articles.A dataset of political Arabic texts collected from diverse sources,including postings and articles,is used to assess the suggested technique.Conservative,reform,and revolutionary are the three subcategories of these opinions.The results of this study demonstrate that compared to other frequently used machine learning models for text classification,the CatBoost method using multi-level features performs better with an accuracy of 98.14%.展开更多
Accurate identification of fungal species is essential for effective diagnosis and treatment.Traditional microscopy-based methods are often subjective and time-consuming.Deep learning has emerged as a promising tool i...Accurate identification of fungal species is essential for effective diagnosis and treatment.Traditional microscopy-based methods are often subjective and time-consuming.Deep learning has emerged as a promising tool in this domain.However,existing deep learning models often struggle to generalise in the presence of class imbalance and subtle morphological differences,which are common in fungal image datasets.This study proposes MASA-Net,a deep learning framework that combines a fine-tuned DenseNet201 backbone with a multi-aspect channel-spatial attention(MASA)module.The attention mechanism refines spatial and channel-wise features by capturing multi-scale spatial patterns and adaptively emphasising informative channels.This enhances the network's ability to focus on diagnostically relevant fungal structures while suppressing irrelevant features.The MASA-Net is evaluated on the DeFungi dataset and demonstrates superior performance in terms of accuracy,precision,recall and F1-score.It also outperforms established attention mechanisms such as squeeze-andexcitation networks(SE)and convolutional block attention module(CBAM)under identical conditions.These results highlight MASA-Net's robustness and effectiveness in addressing class imbalance and structural variability,offering a reliable solution for automated fungal species identification.展开更多
Siamese tracking algorithms usually take convolutional neural networks(CNNs)as feature extractors owing to their capability of extracting deep discriminative features.However,the convolution kernels in CNNs have limit...Siamese tracking algorithms usually take convolutional neural networks(CNNs)as feature extractors owing to their capability of extracting deep discriminative features.However,the convolution kernels in CNNs have limited receptive fields,making it difficult to capture global feature dependencies which is important for object detection,especially when the target undergoes large-scale variations or movement.In view of this,we develop a novel network called effective convolution mixed Transformer Siamese network(SiamCMT)for visual tracking,which integrates CNN-based and Transformer-based architectures to capture both local information and long-range dependencies.Specifically,we design a Transformer-based module named lightweight multi-head attention(LWMHA)which can be flexibly embedded into stage-wise CNNs and improve the network’s representation ability.Additionally,we introduce a stage-wise feature aggregation mechanism which integrates features learned from multiple stages.By leveraging both location and semantic information,this mechanism helps the SiamCMT to better locate and find the target.Moreover,to distinguish the contribution of different channels,a channel-wise attention mechanism is introduced to enhance the important channels and suppress the others.Extensive experiments on seven challenging benchmarks,i.e.,OTB2015,UAV123,GOT10K,LaSOT,DTB70,UAVTrack112_L,and VOT2018,demonstrate the effectiveness of the proposed algorithm.Specially,the proposed method outperforms the baseline by 3.5%and 3.1%in terms of precision and success rates with a real-time speed of 59.77 FPS on UAV123.展开更多
Rain streaks introduced by atmospheric precipitation significantly degrade image quality and impair the reliability of high-level vision tasks.We present a novel image deraining framework built on a three-stage dual-r...Rain streaks introduced by atmospheric precipitation significantly degrade image quality and impair the reliability of high-level vision tasks.We present a novel image deraining framework built on a three-stage dual-residual architecture that progressively restores rain-degraded content while preserving fine structural details.Each stage begins with a multi-scale feature extractor and a channel attention module that adaptively emphasizes informative representations for rain removal.The core restoration is achieved via enhanced dual-residual blocks,which stabilize training and mitigate feature degradation across layers.To further refine representations,we integrate crossdimensional spatial attention supervised by ground-truth guidance,ensuring that only high-quality features propagate to subsequent stages.Inter-stage feature fusion modules are employed to aggregate complementary information,reinforcing reconstruction continuity and consistency.Extensive experiments on five benchmark datasets(Rain100H,Rain100L,RainKITTI2012,RainKITTI2015,and JRSRD)demonstrate that our method establishes new state-of-the-art results in both fidelity and perceptual quality,effectively removing rain streaks while preserving natural textures and structural integrity.展开更多
Human–object interaction(HOI)detection is crucial for human-centric image understanding which aims to infer human,action,object triplets within an image.Recent studies often exploit visual features and the spatial co...Human–object interaction(HOI)detection is crucial for human-centric image understanding which aims to infer human,action,object triplets within an image.Recent studies often exploit visual features and the spatial configuration of a human–object pair in order to learn the action linking the human and object in the pair.We argue that such a paradigm of pairwise feature extraction and action inference can be applied not only at the whole human and object instance level,but also at the part level at which a body part interacts with an object,and at the semantic level by considering the semantic label of an object along with human appearance and human–object spatial configuration,to infer the action.We thus propose a multi-level pairwise feature network(PFNet)for detecting human–object interactions.The network consists of three parallel streams to characterize HOI utilizing pairwise features at the above three levels;the three streams are finally fused to give the action prediction.Extensive experiments show that our proposed PFNet outperforms other state-of-the-art methods on the VCOCO dataset and achieves comparable results to the state-of-the-art on the HICO-DET dataset.展开更多
文摘In this paper we discuss policy iteration methods for approximate solution of a finite-state discounted Markov decision problem, with a focus on feature-based aggregation methods and their connection with deep reinforcement learning schemes. We introduce features of the states of the original problem, and we formulate a smaller "aggregate" Markov decision problem, whose states relate to the features. We discuss properties and possible implementations of this type of aggregation, including a new approach to approximate policy iteration. In this approach the policy improvement operation combines feature-based aggregation with feature construction using deep neural networks or other calculations. We argue that the cost function of a policy may be approximated much more accurately by the nonlinear function of the features provided by aggregation, than by the linear function of the features provided by neural networkbased reinforcement learning, thereby potentially leading to more effective policy improvement.
文摘Aiming at the problem of low detection accuracy due to the different scale sizes of apple leaf disease spots and their similarity to the background,this paper proposes a multi-scale lightweight network(MSL-Net).Firstly,a multiplexed aggregated feature extraction network is proposed using residual bottleneck block(RES-Bottleneck)and middle partial-convolution(MP-Conv)to capture multi-scale spatial features and enhance focus on disease features for better differentiation between disease targets and background information.Secondly,a lightweight feature fusion network is designed using scale-fuse concatenation(SF-Cat)and triple-scale sequence feature fusion(TSSF)module to merge multi-scale feature maps comprehensively.Depthwise convolution(DWConv)and GhostNet lighten the network,while the cross stage partial bottleneck with 3 convolutions ghost-normalization attention module(C3-GN)reduces missed detections by suppressing irrelevant background information.Finally,soft non-maximum suppression(Soft-NMS)is used in the post-processing stage to improve the problem of misdetection of dense disease sites.The results show that the MSL-Net improves mean average precision at intersection over union of 0.5(mAP@0.5)by 2.0%over the baseline you only look once version 5s(YOLOv5s)and reduces parameters by 44%,reducing computation by 27%,outperforming other state-of-the-art(SOTA)models overall.This method also shows excellent performance compared to the latest research.
基金suported by the Fundamental Research Grant Scheme(FRGS)of Universiti Sains Malaysia,Research Number:FRGS/1/2024/ICT02/USM/02/1.
文摘Classroom behavior recognition is a hot research topic,which plays a vital role in assessing and improving the quality of classroom teaching.However,existing classroom behavior recognition methods have challenges for high recognition accuracy with datasets with problems such as scenes with blurred pictures,and inconsistent objects.To address this challenge,we proposed an effective,lightweight object detector method called the RFNet model(YOLO-FR).The YOLO-FR is a lightweight and effective model.Specifically,for efficient multi-scale feature extraction,effective feature pyramid shared convolutional(FPSC)was designed to improve the feature extract performance by leveraging convolutional layers with varying dilation rates from the input image in the backbone.Secondly,to address the problem of multi-scale variability in the scene,we design the Rep Ghost fusion Cross Stage Partial and Efficient Layer Aggregation Network(RGCSPELAN)to improve the network performance further and reduce the amount of computation and the number of parameters.In addition,by conducting experimental valuation on the SCB dataset3 and STBD-08 dataset.Experimental results indicate that,compared to the baseline model,the RFNet model has increased mean accuracy precision(mAP@50)from 69.6%to 71.0%on the SCB dataset3 and from 91.8%to 93.1%on the STBD-08 dataset.The RFNet approach has effectiveness precision at 68.6%,surpassing the baseline method(YOLOv11)at 3.3%and archieve the minimal size(4.9 M)on the SCB dataset3.Finally,comparing it with other algorithms,it accurately detects student behavior in complex classroom environments results confirmed that RFNet is well-suited for real-time and efficiently recognizing classroom behaviors.
文摘The number of blogs and other forms of opinionated online content has increased dramatically in recent years.Many fields,including academia and national security,place an emphasis on automated political article orientation detection.Political articles(especially in the Arab world)are different from other articles due to their subjectivity,in which the author’s beliefs and political affiliation might have a significant influence on a political article.With categories representing the main political ideologies,this problem may be thought of as a subset of the text categorization(classification).In general,the performance of machine learning models for text classification is sensitive to hyperparameter settings.Furthermore,the feature vector used to represent a document must capture,to some extent,the complex semantics of natural language.To this end,this paper presents an intelligent system to detect political Arabic article orientation that adapts the categorical boosting(CatBoost)method combined with a multi-level feature concept.Extracting features at multiple levels can enhance the model’s ability to discriminate between different classes or patterns.Each level may capture different aspects of the input data,contributing to a more comprehensive representation.CatBoost,a robust and efficient gradient-boosting algorithm,is utilized to effectively learn and predict the complex relationships between these features and the political orientation labels associated with the articles.A dataset of political Arabic texts collected from diverse sources,including postings and articles,is used to assess the suggested technique.Conservative,reform,and revolutionary are the three subcategories of these opinions.The results of this study demonstrate that compared to other frequently used machine learning models for text classification,the CatBoost method using multi-level features performs better with an accuracy of 98.14%.
文摘Accurate identification of fungal species is essential for effective diagnosis and treatment.Traditional microscopy-based methods are often subjective and time-consuming.Deep learning has emerged as a promising tool in this domain.However,existing deep learning models often struggle to generalise in the presence of class imbalance and subtle morphological differences,which are common in fungal image datasets.This study proposes MASA-Net,a deep learning framework that combines a fine-tuned DenseNet201 backbone with a multi-aspect channel-spatial attention(MASA)module.The attention mechanism refines spatial and channel-wise features by capturing multi-scale spatial patterns and adaptively emphasising informative channels.This enhances the network's ability to focus on diagnostically relevant fungal structures while suppressing irrelevant features.The MASA-Net is evaluated on the DeFungi dataset and demonstrates superior performance in terms of accuracy,precision,recall and F1-score.It also outperforms established attention mechanisms such as squeeze-andexcitation networks(SE)and convolutional block attention module(CBAM)under identical conditions.These results highlight MASA-Net's robustness and effectiveness in addressing class imbalance and structural variability,offering a reliable solution for automated fungal species identification.
基金supported by the National Natural Science Foundation of China(Grant No.62033007)the Major Fundamental Research Program of Shandong Province(Grant No.ZR2023ZD37).
文摘Siamese tracking algorithms usually take convolutional neural networks(CNNs)as feature extractors owing to their capability of extracting deep discriminative features.However,the convolution kernels in CNNs have limited receptive fields,making it difficult to capture global feature dependencies which is important for object detection,especially when the target undergoes large-scale variations or movement.In view of this,we develop a novel network called effective convolution mixed Transformer Siamese network(SiamCMT)for visual tracking,which integrates CNN-based and Transformer-based architectures to capture both local information and long-range dependencies.Specifically,we design a Transformer-based module named lightweight multi-head attention(LWMHA)which can be flexibly embedded into stage-wise CNNs and improve the network’s representation ability.Additionally,we introduce a stage-wise feature aggregation mechanism which integrates features learned from multiple stages.By leveraging both location and semantic information,this mechanism helps the SiamCMT to better locate and find the target.Moreover,to distinguish the contribution of different channels,a channel-wise attention mechanism is introduced to enhance the important channels and suppress the others.Extensive experiments on seven challenging benchmarks,i.e.,OTB2015,UAV123,GOT10K,LaSOT,DTB70,UAVTrack112_L,and VOT2018,demonstrate the effectiveness of the proposed algorithm.Specially,the proposed method outperforms the baseline by 3.5%and 3.1%in terms of precision and success rates with a real-time speed of 59.77 FPS on UAV123.
基金supported by Key Scientific and Technological Research Program of Henan Province(Grant No.252102211111).
文摘Rain streaks introduced by atmospheric precipitation significantly degrade image quality and impair the reliability of high-level vision tasks.We present a novel image deraining framework built on a three-stage dual-residual architecture that progressively restores rain-degraded content while preserving fine structural details.Each stage begins with a multi-scale feature extractor and a channel attention module that adaptively emphasizes informative representations for rain removal.The core restoration is achieved via enhanced dual-residual blocks,which stabilize training and mitigate feature degradation across layers.To further refine representations,we integrate crossdimensional spatial attention supervised by ground-truth guidance,ensuring that only high-quality features propagate to subsequent stages.Inter-stage feature fusion modules are employed to aggregate complementary information,reinforcing reconstruction continuity and consistency.Extensive experiments on five benchmark datasets(Rain100H,Rain100L,RainKITTI2012,RainKITTI2015,and JRSRD)demonstrate that our method establishes new state-of-the-art results in both fidelity and perceptual quality,effectively removing rain streaks while preserving natural textures and structural integrity.
基金supported by the National Natural Science Foundation of China(Project No.61902210),a Research Grant of Beijing Higher Institution Engineering Research Center,and the Tsinghua–Tencent Joint Laboratory for Internet Innovation Technology.
文摘Human–object interaction(HOI)detection is crucial for human-centric image understanding which aims to infer human,action,object triplets within an image.Recent studies often exploit visual features and the spatial configuration of a human–object pair in order to learn the action linking the human and object in the pair.We argue that such a paradigm of pairwise feature extraction and action inference can be applied not only at the whole human and object instance level,but also at the part level at which a body part interacts with an object,and at the semantic level by considering the semantic label of an object along with human appearance and human–object spatial configuration,to infer the action.We thus propose a multi-level pairwise feature network(PFNet)for detecting human–object interactions.The network consists of three parallel streams to characterize HOI utilizing pairwise features at the above three levels;the three streams are finally fused to give the action prediction.Extensive experiments show that our proposed PFNet outperforms other state-of-the-art methods on the VCOCO dataset and achieves comparable results to the state-of-the-art on the HICO-DET dataset.
