{"url":"/task/camouflaged-object-segmentation","name":"Camouflaged Object Segmentation","slug":"camouflaged-object-segmentation","description_markdown":"Camouflaged object segmentation (COS) or Camouflaged object detection (COD), which was originally promoted by [T.-N. Le et al.](https://www.sciencedirect.com/science/article/abs/pii/S1077314219300608) (2017), aims to identify objects that conceal their texture into the surrounding environment. The high intrinsic similarities between the target object and the background make COS/COD far more challenging than the traditional object segmentation task. Also, refer to the online benchmarks on [CAMO dataset](https://sites.google.com/view/ltnghia/research/camo), [COD dataset](http://dpfan.net/Camouflage/), and [online demo](http://mc.nankai.edu.cn/cod).\r\n\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image source: [Anabranch Network for Camouflaged Object Segmentation](https://www.sciencedirect.com/science/article/abs/pii/S1077314219300608) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":47,"papers_with_code":38,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":7,"subtasks":1,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/camouflaged-object-segmentation-on-pcod-1200","slug":"camouflaged-object-segmentation-on-pcod-1200","dataset":"PCOD_1200","dataset_url":null,"rows_in_archive":16,"metrics":["S-Measure"],"first_row_in_archive_order":{"model":"CMX","paper_title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","paper_url":"/paper/cmx-cross-modal-fusion-for-rgb-x-semantic","paper_date":"2022-03-09","arxiv_id":"2203.04838","code_links":[{"title":"huaaaliu/rgbx_semantic_segmentation","url":"https://github.com/huaaaliu/rgbx_semantic_segmentation"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/camouflaged-object-segmentation-on-camo","slug":"camouflaged-object-segmentation-on-camo","dataset":"CAMO","dataset_url":"/dataset/camo","rows_in_archive":14,"metrics":["S-Measure","Weighted F-Measure","MAE"],"first_row_in_archive_order":{"model":"FOCUS","paper_title":"FOCUS: Towards Universal Foreground Segmentation","paper_url":"/paper/focus-towards-universal-foreground","paper_date":"2025-01-09","arxiv_id":"2501.05238","code_links":[{"title":"geshang777/FOCUS","url":"https://github.com/geshang777/FOCUS"}],"syntology":null}},{"leaderboard":"/sota/camouflaged-object-segmentation-on-cod","slug":"camouflaged-object-segmentation-on-cod","dataset":"COD","dataset_url":"/dataset/cod10k","rows_in_archive":12,"metrics":["S-Measure","Weighted F-Measure","MAE"],"first_row_in_archive_order":{"model":"BiRefNet","paper_title":"Bilateral Reference for High-Resolution Dichotomous Image Segmentation","paper_url":"/paper/bilateral-reference-for-high-resolution","paper_date":"2024-01-07","arxiv_id":"2401.03407","code_links":[{"title":"zhengpeng7/birefnet","url":"https://github.com/zhengpeng7/birefnet"}],"syntology":{"n":14,"n_ran":13,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/camouflaged-object-segmentation-on-chameleon","slug":"camouflaged-object-segmentation-on-chameleon","dataset":"CHAMELEON","dataset_url":null,"rows_in_archive":6,"metrics":["S-measure","weighted F-measure","MAE"],"first_row_in_archive_order":{"model":"BiRefNet","paper_title":"Bilateral Reference for High-Resolution Dichotomous Image Segmentation","paper_url":"/paper/bilateral-reference-for-high-resolution","paper_date":"2024-01-07","arxiv_id":"2401.03407","code_links":[{"title":"zhengpeng7/birefnet","url":"https://github.com/zhengpeng7/birefnet"}],"syntology":{"n":14,"n_ran":13,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/camouflaged-object-segmentation-on-nc4k","slug":"camouflaged-object-segmentation-on-nc4k","dataset":"NC4K","dataset_url":"/dataset/nc4k","rows_in_archive":6,"metrics":["S-measure","weighted F-measure","MAE"],"first_row_in_archive_order":{"model":"FOCUS","paper_title":"FOCUS: Towards Universal Foreground Segmentation","paper_url":"/paper/focus-towards-universal-foreground","paper_date":"2025-01-09","arxiv_id":"2501.05238","code_links":[{"title":"geshang777/FOCUS","url":"https://github.com/geshang777/FOCUS"}],"syntology":null}},{"leaderboard":"/sota/camouflaged-object-segmentation-on-moca-mask","slug":"camouflaged-object-segmentation-on-moca-mask","dataset":"MoCA-Mask","dataset_url":"/dataset/moca-mask","rows_in_archive":4,"metrics":["S-measure","weighted F-measure","MAE","mDice","mIoU"],"first_row_in_archive_order":{"model":"ZS-VCOS","paper_title":"ZS-VCOS: Zero-Shot Outperforms Supervised Video Camouflaged Object Segmentation with Zero-Shot Method","paper_url":"/paper/zs-vcos-zero-shot-outperforms-supervised","paper_date":"2025-03-30","arxiv_id":null,"code_links":[{"title":"weathon/vcos","url":"https://github.com/weathon/vcos"}],"syntology":null}},{"leaderboard":"/sota/camouflaged-object-segmentation-on","slug":"camouflaged-object-segmentation-on","dataset":"Camouflaged Animal Dataset","dataset_url":"/dataset/camouflaged-animal-dataset","rows_in_archive":2,"metrics":["S-measure","weighted F-measure","MAE","mDice","mIoU"],"first_row_in_archive_order":{"model":"ZoomNeXt-PVTv2-B5","paper_title":"ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection","paper_url":"/paper/zoomnext-a-unified-collaborative-pyramid","paper_date":"2023-10-31","arxiv_id":"2310.20208","code_links":[{"title":"lartpang/zoomnext","url":"https://github.com/lartpang/zoomnext"}],"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":11}}}],"datasets":[{"url":"/dataset/cod10k","name":"COD10K","full_name":"Camouflaged/Concealed Object Detection","num_papers_in_archive":166},{"url":"/dataset/camo","name":"CAMO","full_name":"Camouflaged Object","num_papers_in_archive":139},{"url":"/dataset/nc4k","name":"NC4K","full_name":"","num_papers_in_archive":94},{"url":"/dataset/moca-mask","name":"MoCA-Mask","full_name":"Moving Camouflaged Animals (MoCA)-Mask","num_papers_in_archive":17},{"url":"/dataset/camo-1","name":"CAMO++","full_name":"","num_papers_in_archive":8},{"url":"/dataset/camouflaged-animal-dataset","name":"Camouflaged Animal Dataset","full_name":"Camouflaged Animal Dataset","num_papers_in_archive":4},{"url":"/dataset/r2c7k","name":"R2C7K","full_name":"","num_papers_in_archive":3}],"subtasks":[{"url":"/task/camouflaged-object-segmentation-with-a-single","name":"Camouflaged Object Segmentation with a Single Task-generic Prompt"}],"parent_tasks":[{"url":"/task/object-detection","name":"Object Detection"},{"url":"/task/object-segmentation","name":"Object Segmentation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":38,"tagged_in_all":47,"items":[{"url":"/paper/unet-a-nested-u-net-architecture-for-medical","title":"UNet++: A Nested U-Net Architecture for Medical Image Segmentation","date":"2018-07-18","arxiv_id":"1807.10165","repositories_listed":34,"syntology":{"n":28,"n_ran":6,"n_unverified":22,"n_pointer_only":2}},{"url":"/paper/egnet-edge-guidance-network-for-salient","title":"EGNet: Edge Guidance Network for Salient Object Detection","date":"2019-10-01","arxiv_id":null,"repositories_listed":7,"syntology":null},{"url":"/paper/boundary-aware-segmentation-network-for","title":"Boundary-Aware Segmentation Network for Mobile and Web Applications","date":"2021-01-12","arxiv_id":"2101.04704","repositories_listed":5,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/pranet-parallel-reverse-attention-network-for","title":"PraNet: Parallel Reverse Attention Network for Polyp Segmentation","date":"2020-06-13","arxiv_id":"2006.11392","repositories_listed":4,"syntology":{"n":9,"n_ran":8,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/f3net-fusion-feedback-and-focus-for-salient","title":"F3Net: Fusion, Feedback and Focus for Salient Object Detection","date":"2019-11-26","arxiv_id":"1911.11445","repositories_listed":4,"syntology":null},{"url":"/paper/basnet-boundary-aware-salient-object","title":"BASNet: Boundary-Aware Salient Object Detection","date":"2019-06-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/integrating-extra-modality-helps-segmentor","title":"Integrating Extra Modality Helps Segmentor Find Camouflaged Objects Well","date":"2025-02-20","arxiv_id":"2502.14471","repositories_listed":2,"syntology":null},{"url":"/paper/explicit-visual-prompting-for-universal","title":"Explicit Visual Prompting for Universal Foreground Segmentations","date":"2023-05-29","arxiv_id":"2305.18476","repositories_listed":2,"syntology":null},{"url":"/paper/camouflaged-object-detection-via-context","title":"Camouflaged Object Detection via Context-aware Cross-level Fusion","date":"2022-07-27","arxiv_id":"2207.13362","repositories_listed":2,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/context-aware-cross-level-fusion-network-for","title":"Context-aware Cross-level Fusion Network for Camouflaged Object Detection","date":"2021-05-26","arxiv_id":"2105.12555","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/anabranch-network-for-camouflaged-object-1","title":"Anabranch Network for Camouflaged Object Segmentation","date":"2021-05-20","arxiv_id":"2105.09451","repositories_listed":2,"syntology":null},{"url":"/paper/transformer-transforms-salient-object","title":"Generative Transformer for Accurate and Reliable Salient Object Detection","date":"2021-04-20","arxiv_id":"2104.10127","repositories_listed":2,"syntology":null},{"url":"/paper/camouflaged-object-detection","title":"Camouflaged Object Detection","date":"2020-06-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/open-vocabulary-camouflaged-object-1","title":"Open-Vocabulary Camouflaged Object Segmentation with Cascaded Vision Language Models","date":"2025-06-24","arxiv_id":"2506.19300","repositories_listed":1,"syntology":null},{"url":"/paper/stepwise-decomposition-and-dual-stream-focus","title":"Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentation","date":"2025-06-07","arxiv_id":"2506.06818","repositories_listed":1,"syntology":null},{"url":"/paper/zs-vcos-zero-shot-outperforms-supervised-1","title":"ZS-VCOS: Zero-Shot Outperforms Supervised Video Camouflaged Object Segmentation","date":"2025-04-10","arxiv_id":"2505.01431","repositories_listed":1,"syntology":null},{"url":"/paper/zs-vcos-zero-shot-outperforms-supervised","title":"ZS-VCOS: Zero-Shot Outperforms Supervised Video Camouflaged Object Segmentation with Zero-Shot Method","date":"2025-03-30","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/camsam2-segment-anything-accurately-in","title":"CamSAM2: Segment Anything Accurately in Camouflaged Videos","date":"2025-03-25","arxiv_id":"2503.19730","repositories_listed":1,"syntology":null},{"url":"/paper/focus-towards-universal-foreground","title":"FOCUS: Towards Universal Foreground Segmentation","date":"2025-01-09","arxiv_id":"2501.05238","repositories_listed":1,"syntology":null},{"url":"/paper/when-sam2-meets-video-camouflaged-object","title":"When SAM2 Meets Video Camouflaged Object Segmentation: A Comprehensive Evaluation and Adaptation","date":"2024-09-27","arxiv_id":"2409.18653","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-hallucinations-to-reduce-manual","title":"Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentation","date":"2024-08-27","arxiv_id":"2408.15205","repositories_listed":1,"syntology":{"n":9,"n_ran":2,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/unlocking-attributes-contribution-to","title":"Unlocking Attributes' Contribution to Successful Camouflage: A Combined Textual and VisualAnalysis Strategy","date":"2024-08-22","arxiv_id":"2408.12086","repositories_listed":1,"syntology":null},{"url":"/paper/bilateral-reference-for-high-resolution","title":"Bilateral Reference for High-Resolution Dichotomous Image Segmentation","date":"2024-01-07","arxiv_id":"2401.03407","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/open-vocabulary-camouflaged-object","title":"Open-Vocabulary Camouflaged Object Segmentation","date":"2023-11-19","arxiv_id":"2311.11241","repositories_listed":1,"syntology":null},{"url":"/paper/zoomnext-a-unified-collaborative-pyramid","title":"ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection","date":"2023-10-31","arxiv_id":"2310.20208","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":11}},{"url":"/paper/unsupervised-camouflaged-object-segmentation","title":"Unsupervised Camouflaged Object Segmentation as Domain Adaptation","date":"2023-08-08","arxiv_id":"2308.04528","repositories_listed":1,"syntology":null},{"url":"/paper/improving-existing-segmentators-performance","title":"Improving existing segmentators performance with zero-shot segmentators","date":"2023-07-26","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/edge-aware-mirror-network-for-camouflaged","title":"Edge-Aware Mirror Network for Camouflaged Object Detection","date":"2023-07-08","arxiv_id":"2307.03932","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-camouflaged-animal-detection-and","title":"The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentation","date":"2023-04-15","arxiv_id":"2304.07444","repositories_listed":1,"syntology":null},{"url":"/paper/explicit-visual-prompting-for-low-level","title":"Explicit Visual Prompting for Low-Level Structure Segmentations","date":"2023-03-20","arxiv_id":"2303.10883","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}}],"syntology_records":9,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}