{"ID":5675227,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-05T08:10:22.076508179Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01870","arxiv_id":"2607.01870","title":"CamoNAS: Neural Architecture Search for Enhanced Camouflaged Object Detection","abstract":"Camouflaged Object Detection (COD) aims to locate and segment objects that blend into their surroundings, presenting challenges due to weak edge cues and ill-defined boundaries. Traditional COD models rely on hand-designed architectures and multi-scale feature fusion, which are often guided by intuition rather than systematic search. This paper introduces CamoNAS, a frequency-aware multi-resolution Neural Architecture Search (NAS) framework for COD. CamoNAS automatically searches both cell-level operations and network-level downsampling paths, forming a hierarchical search space tailored to detect camouflaged objects. Additionally, it adopts an RGB frequency dual-stream architecture, where a learnable wavelet transform complements the RGB spatial stream. CamoNAS achieves state-of-the-art performance on four COD benchmarks (CAMO, COD10K, NC4K, CHAMELEON), highlighting the effectiveness of NAS for COD. Our code is available at https://github.com/rendaweiSIMIT/CamoNAS.","short_abstract":"Camouflaged Object Detection (COD) aims to locate and segment objects that blend into their surroundings, presenting challenges due to weak edge cues and ill-defined boundaries. Traditional COD models rely on hand-designed architectures and multi-scale feature fusion, which are often guided by intuition rather than sys...","url_abs":"https://arxiv.org/abs/2607.01870","url_pdf":"https://arxiv.org/pdf/2607.01870v1","authors":"[\"Dawei Ren\",\"Yan Zhang\",\"Hongying Tang\",\"Qiaoling Zhou\",\"Jianpo Liu\"]","published":"2026-07-02T08:25:51Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[]","has_code":false,"code_links":[{"ID":613887,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-03T01:40:09.565152011Z","DeletedAt":null,"paper_id":5675227,"paper_url":"https://arxiv.org/abs/2607.01870","paper_title":"CamoNAS: Neural Architecture Search for Enhanced Camouflaged Object Detection","repo_url":"https://github.com/rendaweiSIMIT/CamoNAS","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}