Pub Date : 2026-01-23DOI: 10.1109/tip.2026.3654770
Can Peng,Manxin Chao,Ruoyu Li,Zaiqing Chen,Lijun Yun,Yuelong Xia
Using higher-resolution feature maps in the network is an effective approach for detecting small objects. However, high-resolution feature maps face the challenge of lacking semantic information. This has led previous methods to rely on downsampling feature maps, applying large-kernel convolution layers, and then upsampling the feature maps to obtain semantic information. However, these methods have certain limitations: first, large kernel convolutions in deeper layers typically provide significant global semantic information, but our experiments reveal that such prominent semantic information introduces background smear, which in turn leads to overfitting. Second, deep features often contain substantial redundant information, and the features of small objects are either minimal or have disappeared, which causes a degradation in detection performance when directly relying on deep features. To address these issues, we propose a high-resolution network based on local contextual semantics (HR-SemNet). The network is built on the proposed high-resolution backbone (HRB), which replaces the traditional backbone-FPN architecture by focusing all computational resources of large kernel convolutions on highresolution feature layers to capture clearer features of small objects. Additionally, a local context semantic module (LCSM) is employed to extract semantic information from the background, confining the semantic extraction to a local window to avoid interference from large-scale backgrounds and objects. HRSemNet decouples small object semantics from contextual semantics, with HRB and LCSM independently extracting these features. Extensive experiments and comprehensive evaluations on the VisDrone, AI-TOD, and TinyPerson datasets validate the effectiveness of the method. On the VisDrone dataset, which contains a large number of small objects, HR-SemNet improves the mean average precision (mAP) by 4.6%, reduces the computational cost (GFLOPs) by 49.9%, and decreases the parameter count by 94.9%.
{"title":"HR-SemNet: A High-Resolution Network for Enhanced Small Object Detection With Local Contextual Semantics.","authors":"Can Peng,Manxin Chao,Ruoyu Li,Zaiqing Chen,Lijun Yun,Yuelong Xia","doi":"10.1109/tip.2026.3654770","DOIUrl":"https://doi.org/10.1109/tip.2026.3654770","url":null,"abstract":"Using higher-resolution feature maps in the network is an effective approach for detecting small objects. However, high-resolution feature maps face the challenge of lacking semantic information. This has led previous methods to rely on downsampling feature maps, applying large-kernel convolution layers, and then upsampling the feature maps to obtain semantic information. However, these methods have certain limitations: first, large kernel convolutions in deeper layers typically provide significant global semantic information, but our experiments reveal that such prominent semantic information introduces background smear, which in turn leads to overfitting. Second, deep features often contain substantial redundant information, and the features of small objects are either minimal or have disappeared, which causes a degradation in detection performance when directly relying on deep features. To address these issues, we propose a high-resolution network based on local contextual semantics (HR-SemNet). The network is built on the proposed high-resolution backbone (HRB), which replaces the traditional backbone-FPN architecture by focusing all computational resources of large kernel convolutions on highresolution feature layers to capture clearer features of small objects. Additionally, a local context semantic module (LCSM) is employed to extract semantic information from the background, confining the semantic extraction to a local window to avoid interference from large-scale backgrounds and objects. HRSemNet decouples small object semantics from contextual semantics, with HRB and LCSM independently extracting these features. Extensive experiments and comprehensive evaluations on the VisDrone, AI-TOD, and TinyPerson datasets validate the effectiveness of the method. On the VisDrone dataset, which contains a large number of small objects, HR-SemNet improves the mean average precision (mAP) by 4.6%, reduces the computational cost (GFLOPs) by 49.9%, and decreases the parameter count by 94.9%.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"31 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146034074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-22DOI: 10.1109/tip.2026.3654892
Xiang Yuan,Gong Cheng,Jiacheng Cheng,Ruixiang Yao,Junwei Han
Small object detection (SOD) constitutes a notable yet immensely arduous task, stemming from the restricted informative regions inherent in size-limited instances, which further sparks off heightened uncertainty beyond the capacity of current two-stage detectors. Specifically, the intrinsic ambiguity in small objects undermines the prevailing sampling paradigms and may mislead the model to devote futile effort to those unrecognizable targets, while the inconsistency of features utilized for the detection at two stages further exposes the hierarchical uncertainty. In this paper, we develop an Uncertainty learning framework for Small Object Detection, dubbed as Unc-SOD. By incorporating an auxiliary uncertainty branch to conventional Region Proposal Network (RPN), we model the indeterminacy at instance-level which later on serves as a surrogate criterion for sampling, thereby unearthing adequate candidates dynamically based on the varying degrees of uncertainty and facilitating the learning of proposal networks. In parallel, a Perception-and-Interaction strategy is devised to capture rich and discriminative representations, through optimizing the intrinsic properties from the regional features at the original pyramid and the assigned one, in which the perceptual process unfolds in a mutual paradigm. As the seminal attempt to model uncertainty in SOD task, our Unc-SOD yields state-of-the-art performance on two large-scale small object detection benchmarks, SODA-D and SODA-A, and the results on several SOD-oriented datasets including COCO, VisDrone, and Tsinghua-Tencent 100K also exhibit the promotion to baseline detector. This underscores the efficacy of our approach and its superiority over prevailing detectors when dealing with small instances.
{"title":"Unc-SOD: An Uncertainty Learning Framework for Small Object Detection.","authors":"Xiang Yuan,Gong Cheng,Jiacheng Cheng,Ruixiang Yao,Junwei Han","doi":"10.1109/tip.2026.3654892","DOIUrl":"https://doi.org/10.1109/tip.2026.3654892","url":null,"abstract":"Small object detection (SOD) constitutes a notable yet immensely arduous task, stemming from the restricted informative regions inherent in size-limited instances, which further sparks off heightened uncertainty beyond the capacity of current two-stage detectors. Specifically, the intrinsic ambiguity in small objects undermines the prevailing sampling paradigms and may mislead the model to devote futile effort to those unrecognizable targets, while the inconsistency of features utilized for the detection at two stages further exposes the hierarchical uncertainty. In this paper, we develop an Uncertainty learning framework for Small Object Detection, dubbed as Unc-SOD. By incorporating an auxiliary uncertainty branch to conventional Region Proposal Network (RPN), we model the indeterminacy at instance-level which later on serves as a surrogate criterion for sampling, thereby unearthing adequate candidates dynamically based on the varying degrees of uncertainty and facilitating the learning of proposal networks. In parallel, a Perception-and-Interaction strategy is devised to capture rich and discriminative representations, through optimizing the intrinsic properties from the regional features at the original pyramid and the assigned one, in which the perceptual process unfolds in a mutual paradigm. As the seminal attempt to model uncertainty in SOD task, our Unc-SOD yields state-of-the-art performance on two large-scale small object detection benchmarks, SODA-D and SODA-A, and the results on several SOD-oriented datasets including COCO, VisDrone, and Tsinghua-Tencent 100K also exhibit the promotion to baseline detector. This underscores the efficacy of our approach and its superiority over prevailing detectors when dealing with small instances.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"1 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2026-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146021636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
object segmentation (VOS) is a fundamental task in video analysis, aiming to accurately recognize and segment objects of interest within video sequences. Conventional methods, relying on memory networks to store single-frame appearance features, face challenges in computational efficiency and capturing dynamic visual information effectively. To address these limitations, we present a Video Decoupling Network (VDN) with a per-clip memory updating mechanism. Our approach is inspired by the dual-stream hypothesis of the human visual cortex and decomposes multiple previous video frames into fundamental elements: scene, motion, and instance. We propose the Unified Prior-based Spatio-temporal Decoupler (UPSD) algorithm, which parses multiple frames into basic elements in a unified manner. UPSD continuously stores elements over time, enabling adaptive integration of different cues based on task requirements. This decomposition mechanism facilitates comprehensive spatial-temporal information capture and rapid updating, leading to notable enhancements in overall VOS performance. Extensive experiments conducted on multiple VOS benchmarks validate the state-of-the-art accuracy, efficiency, generalizability, and robustness of our approach. Remarkably, VDN demonstrates a significant performance improvement and a substantial speed-up compared to previous state-of-the-art methods on multiple VOS benchmarks. It also exhibits excellent generalizability under domain shift and robustness against various noise types.
{"title":"Video Decoupling Networks for Accurate, Efficient, Generalizable, and Robust Video Object Segmentation.","authors":"Jisheng Dang,Huicheng Zheng,Yulan Guo,Jianhuang Lai,Bin Hu,Tat-Seng Chua","doi":"10.1109/tip.2025.3649360","DOIUrl":"https://doi.org/10.1109/tip.2025.3649360","url":null,"abstract":"object segmentation (VOS) is a fundamental task in video analysis, aiming to accurately recognize and segment objects of interest within video sequences. Conventional methods, relying on memory networks to store single-frame appearance features, face challenges in computational efficiency and capturing dynamic visual information effectively. To address these limitations, we present a Video Decoupling Network (VDN) with a per-clip memory updating mechanism. Our approach is inspired by the dual-stream hypothesis of the human visual cortex and decomposes multiple previous video frames into fundamental elements: scene, motion, and instance. We propose the Unified Prior-based Spatio-temporal Decoupler (UPSD) algorithm, which parses multiple frames into basic elements in a unified manner. UPSD continuously stores elements over time, enabling adaptive integration of different cues based on task requirements. This decomposition mechanism facilitates comprehensive spatial-temporal information capture and rapid updating, leading to notable enhancements in overall VOS performance. Extensive experiments conducted on multiple VOS benchmarks validate the state-of-the-art accuracy, efficiency, generalizability, and robustness of our approach. Remarkably, VDN demonstrates a significant performance improvement and a substantial speed-up compared to previous state-of-the-art methods on multiple VOS benchmarks. It also exhibits excellent generalizability under domain shift and robustness against various noise types.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"66 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2026-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146015335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Compared to traditional computed tomography (CT), photon-counting detector (PCD)-based CT provides significant advantages, including enhanced CT image contrast and reduced radiation dose. However, owing to the current immaturity of PCD technology, scanned PCD data often contain stripe artifacts resulting from non-functional or defective detector units, which subsequently introduce ring artifacts in reconstructed CT images. The presence of ring artifact may compromise the accuracy of CT values and even introduce pseudo-structures, thereby reducing the application value of CT images. In this paper, we propose a dual-domain optimization model that takes advantage of the distribution characteristics of stripe artifact in 3D projection data and the prior features of reconstructed 3D CT images. Specifically, we demonstrate that stripe artifact in 3D projection data exhibit both group sparsity and low-rank properties. Building on this observation, we propose a TLT (TV-l2,1- Tucker) model to eliminate ring artifact in PCD-based cone beam CT (CBCT). In addition, an efficient iterative algorithm is designed to solve the proposed model. The effectiveness of both the model and the algorithm is evaluated through simulated and real data experiments. Experimental results demonstrate that the proposed method outperforms existing state-of-the-art approaches.
{"title":"Dual Domain Optimization Algorithm for CBCT Ring Artifact Correction.","authors":"Yanwei Qin,Xiaohui Su,Xin Lu,Baodi Yu,Yunsong Zhao,Fanyong Meng","doi":"10.1109/tip.2026.3652008","DOIUrl":"https://doi.org/10.1109/tip.2026.3652008","url":null,"abstract":"Compared to traditional computed tomography (CT), photon-counting detector (PCD)-based CT provides significant advantages, including enhanced CT image contrast and reduced radiation dose. However, owing to the current immaturity of PCD technology, scanned PCD data often contain stripe artifacts resulting from non-functional or defective detector units, which subsequently introduce ring artifacts in reconstructed CT images. The presence of ring artifact may compromise the accuracy of CT values and even introduce pseudo-structures, thereby reducing the application value of CT images. In this paper, we propose a dual-domain optimization model that takes advantage of the distribution characteristics of stripe artifact in 3D projection data and the prior features of reconstructed 3D CT images. Specifically, we demonstrate that stripe artifact in 3D projection data exhibit both group sparsity and low-rank properties. Building on this observation, we propose a TLT (TV-l2,1- Tucker) model to eliminate ring artifact in PCD-based cone beam CT (CBCT). In addition, an efficient iterative algorithm is designed to solve the proposed model. The effectiveness of both the model and the algorithm is evaluated through simulated and real data experiments. Experimental results demonstrate that the proposed method outperforms existing state-of-the-art approaches.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"81 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2026-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145971760","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-13DOI: 10.1109/tip.2026.3651959
Paolo Giannitrapani, Elio D. Di Claudio, Giovanni Jacovitti
{"title":"BELE: Blur Equivalent Linearized Estimator","authors":"Paolo Giannitrapani, Elio D. Di Claudio, Giovanni Jacovitti","doi":"10.1109/tip.2026.3651959","DOIUrl":"https://doi.org/10.1109/tip.2026.3651959","url":null,"abstract":"","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"37 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2026-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145961757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-13DOI: 10.1109/tip.2026.3651956
Xin Jiang,Ziye Fang,Fei Shen,Junyao Gao,Zechao Li
Ultra-Fine-Grained Visual Categorization (Ultra-FGVC) aims to classify objects into sub-granular categories, presenting the challenge of distinguishing visually similar objects with limited data. Existing methods primarily address sample scarcity but often overlook the importance of leveraging intrinsic object features to construct highly discriminative representations. This limitation significantly constrains their effectiveness in Ultra-FGVC tasks. To address these challenges, we propose SV-Transformer that progressively encodes object features while incorporating background perturbation modeling to generate robust and discriminative representations. At the core of our approach is a progressive feature encoder, which hierarchically extracts global semantic structures and local discriminative details from backbone-generated representations. This design enhances inter-class separability while ensuring resilience to intra-class variations. Furthermore, our background perturbation learning mechanism introduces controlled variations in the feature space, effectively mitigating the impact of sample limitations and improving the model's capacity to capture fine-grained distinctions. Comprehensive experiments demonstrate that SV-Transformer achieves state-of-the-art performance on benchmark Ultra-FGVC datasets, showcasing its efficacy in addressing the challenges of Ultra-FGVC task.
{"title":"Progressive Feature Encoding with Background Perturbation Learning for Ultra-Fine-Grained Visual Categorization.","authors":"Xin Jiang,Ziye Fang,Fei Shen,Junyao Gao,Zechao Li","doi":"10.1109/tip.2026.3651956","DOIUrl":"https://doi.org/10.1109/tip.2026.3651956","url":null,"abstract":"Ultra-Fine-Grained Visual Categorization (Ultra-FGVC) aims to classify objects into sub-granular categories, presenting the challenge of distinguishing visually similar objects with limited data. Existing methods primarily address sample scarcity but often overlook the importance of leveraging intrinsic object features to construct highly discriminative representations. This limitation significantly constrains their effectiveness in Ultra-FGVC tasks. To address these challenges, we propose SV-Transformer that progressively encodes object features while incorporating background perturbation modeling to generate robust and discriminative representations. At the core of our approach is a progressive feature encoder, which hierarchically extracts global semantic structures and local discriminative details from backbone-generated representations. This design enhances inter-class separability while ensuring resilience to intra-class variations. Furthermore, our background perturbation learning mechanism introduces controlled variations in the feature space, effectively mitigating the impact of sample limitations and improving the model's capacity to capture fine-grained distinctions. Comprehensive experiments demonstrate that SV-Transformer achieves state-of-the-art performance on benchmark Ultra-FGVC datasets, showcasing its efficacy in addressing the challenges of Ultra-FGVC task.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"391 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2026-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145961420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Confined spaces refer to partially or fully enclosed areas, e.g., sewage wells, where working conditions pose significant risks to the workers. The evaluation of COfined Space Operational Safety (COSOS) refers to verifying whether workers are properly equipped with safety equipment before entering a confined space, which is crucial for protecting their safety and health. Due to the crowded nature of such environments and the small size of certain safety equipment, existing methods face significant challenges. Moreover, there is a lack of dedicated datasets to support research in this domain. In this paper, in order to advance research in this challenging task, we present COSOS-1k, an extensive dataset constructed from diverse confined space scenarios. It comprises multi-view videos for each scenario, covers 10 essential safety protective equipments and 6 attributes of worker, and is annotated with expressive object locations, fine-grained attributes, and occlusion status. The COSOS-1k is the first dataset known to date, tailored explicitly for the real-world COSOS scenarios. In addition, we address the challenge of occlusion from three perspectives: instance, video, and view. Firstly, at the instance level, we propose Occlusion-aware Uncertainty Estimation (OUE) method, which leverages box-level occlusion annotations to enable part-level occlusion prediction for objects. Secondly, at the video level, we introduce Cross-Frame Cluster (CFC) attention, which integrates temporal context features from the same object category to mitigate the impact of occlusions in the current frame. Finally, we extend CFC to the view level and form Cross-View Cluster (CVC) attention, where complementary information is mined from another view. Extensive experiments demonstrate the effectiveness of the proposed methods and provide insights into the importance of dataset diversity and expressivity. The COSOS-1k dataset and code are available at https://github.com/deepalchemist/cosos-1k.
{"title":"COSOS-1k: A Benchmark Dataset and Occlusion-aware Uncertainty Learning for Multi-view Video Object Detection.","authors":"Wenjie Yang,Yueying Kao,Tong Liu,Yuanlong Yu,Kaiqi Huang","doi":"10.1109/tip.2026.3651950","DOIUrl":"https://doi.org/10.1109/tip.2026.3651950","url":null,"abstract":"Confined spaces refer to partially or fully enclosed areas, e.g., sewage wells, where working conditions pose significant risks to the workers. The evaluation of COfined Space Operational Safety (COSOS) refers to verifying whether workers are properly equipped with safety equipment before entering a confined space, which is crucial for protecting their safety and health. Due to the crowded nature of such environments and the small size of certain safety equipment, existing methods face significant challenges. Moreover, there is a lack of dedicated datasets to support research in this domain. In this paper, in order to advance research in this challenging task, we present COSOS-1k, an extensive dataset constructed from diverse confined space scenarios. It comprises multi-view videos for each scenario, covers 10 essential safety protective equipments and 6 attributes of worker, and is annotated with expressive object locations, fine-grained attributes, and occlusion status. The COSOS-1k is the first dataset known to date, tailored explicitly for the real-world COSOS scenarios. In addition, we address the challenge of occlusion from three perspectives: instance, video, and view. Firstly, at the instance level, we propose Occlusion-aware Uncertainty Estimation (OUE) method, which leverages box-level occlusion annotations to enable part-level occlusion prediction for objects. Secondly, at the video level, we introduce Cross-Frame Cluster (CFC) attention, which integrates temporal context features from the same object category to mitigate the impact of occlusions in the current frame. Finally, we extend CFC to the view level and form Cross-View Cluster (CVC) attention, where complementary information is mined from another view. Extensive experiments demonstrate the effectiveness of the proposed methods and provide insights into the importance of dataset diversity and expressivity. The COSOS-1k dataset and code are available at https://github.com/deepalchemist/cosos-1k.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"26 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2026-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145961417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：