{"title":"基于PVTv2的伪装目标检测边缘引导语义感知网络","authors":"Hongbo Bi, Jianing Yu, Disen Mo, Shiyuan Li, Cong Zhang","doi":"10.1016/j.imavis.2025.105720","DOIUrl":null,"url":null,"abstract":"<div><div>Camouflaged object detection (COD) attempts to identify and segment objects visually blended into their surroundings, presenting significant challenges in complex real-world scenarios. Despite growing attention, existing COD methods often yield unsatisfactory performance, primarily due to their inadequate integration of edge information and semantic context—a critical shortcoming when handling intricate scenes. To this end, we propose a novel Edge-guided Semantic-aware Network (ESNet) that explicitly leverages the synergy between edge cues and multi-scale semantics. Our framework incorporates two key components: a Context-Aware Aggregation with Edge Guidance (CAEG) module, which utilizes edge information to refine object boundaries and enhance feature representation across scales, and a Cross-layer Semantic-Refinement Fusion (CSF) module, designed to aggregate and reinforce multi-level semantic context for richer feature characterization. Numerous experiments on three challenging benchmark datasets demonstrate that the proposed ESNet outperforms 17 state-of-the-art algorithms, achieving new standards in detection accuracy and robustness.</div></div>","PeriodicalId":50374,"journal":{"name":"Image and Vision Computing","volume":"162 ","pages":"Article 105720"},"PeriodicalIF":4.2000,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Edge-guided semantic-aware network for camouflaged object detection with PVTv2\",\"authors\":\"Hongbo Bi, Jianing Yu, Disen Mo, Shiyuan Li, Cong Zhang\",\"doi\":\"10.1016/j.imavis.2025.105720\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Camouflaged object detection (COD) attempts to identify and segment objects visually blended into their surroundings, presenting significant challenges in complex real-world scenarios. Despite growing attention, existing COD methods often yield unsatisfactory performance, primarily due to their inadequate integration of edge information and semantic context—a critical shortcoming when handling intricate scenes. To this end, we propose a novel Edge-guided Semantic-aware Network (ESNet) that explicitly leverages the synergy between edge cues and multi-scale semantics. Our framework incorporates two key components: a Context-Aware Aggregation with Edge Guidance (CAEG) module, which utilizes edge information to refine object boundaries and enhance feature representation across scales, and a Cross-layer Semantic-Refinement Fusion (CSF) module, designed to aggregate and reinforce multi-level semantic context for richer feature characterization. Numerous experiments on three challenging benchmark datasets demonstrate that the proposed ESNet outperforms 17 state-of-the-art algorithms, achieving new standards in detection accuracy and robustness.</div></div>\",\"PeriodicalId\":50374,\"journal\":{\"name\":\"Image and Vision Computing\",\"volume\":\"162 \",\"pages\":\"Article 105720\"},\"PeriodicalIF\":4.2000,\"publicationDate\":\"2025-08-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Image and Vision Computing\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0262885625003087\",\"RegionNum\":3,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Image and Vision Computing","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0262885625003087","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
Edge-guided semantic-aware network for camouflaged object detection with PVTv2
Camouflaged object detection (COD) attempts to identify and segment objects visually blended into their surroundings, presenting significant challenges in complex real-world scenarios. Despite growing attention, existing COD methods often yield unsatisfactory performance, primarily due to their inadequate integration of edge information and semantic context—a critical shortcoming when handling intricate scenes. To this end, we propose a novel Edge-guided Semantic-aware Network (ESNet) that explicitly leverages the synergy between edge cues and multi-scale semantics. Our framework incorporates two key components: a Context-Aware Aggregation with Edge Guidance (CAEG) module, which utilizes edge information to refine object boundaries and enhance feature representation across scales, and a Cross-layer Semantic-Refinement Fusion (CSF) module, designed to aggregate and reinforce multi-level semantic context for richer feature characterization. Numerous experiments on three challenging benchmark datasets demonstrate that the proposed ESNet outperforms 17 state-of-the-art algorithms, achieving new standards in detection accuracy and robustness.
期刊介绍:
Image and Vision Computing has as a primary aim the provision of an effective medium of interchange for the results of high quality theoretical and applied research fundamental to all aspects of image interpretation and computer vision. The journal publishes work that proposes new image interpretation and computer vision methodology or addresses the application of such methods to real world scenes. It seeks to strengthen a deeper understanding in the discipline by encouraging the quantitative comparison and performance evaluation of the proposed methodology. The coverage includes: image interpretation, scene modelling, object recognition and tracking, shape analysis, monitoring and surveillance, active vision and robotic systems, SLAM, biologically-inspired computer vision, motion analysis, stereo vision, document image understanding, character and handwritten text recognition, face and gesture recognition, biometrics, vision-based human-computer interaction, human activity and behavior understanding, data fusion from multiple sensor inputs, image databases.