{"url":"/task/camouflaged-object-segmentation-with-a-single","name":"Camouflaged Object Segmentation with a Single Task-generic Prompt","slug":"camouflaged-object-segmentation-with-a-single","description_markdown":"The previous fully-supervised and weakly-supervised camouflaged object segmentation tasks required a significant amount of annotated data for supervised training to enable models to segment camouflaged objects effectively. However, models like the Segment Anything Model (SAM), which falls under the category of Promptable Segmentation models, can achieve excellent segmentation performance on unseen images with just an instance-specific visual prompt. Nevertheless, for complex scenarios like camouflaged objects, SAM may not perform well even with an instance-specific prompt. Furthermore, the question arises: Is an instance-specific prompt necessary? In more realistic scenarios, where only a task-generic task description is provided as a universally applicable text prompt, how can we improve segmentation across various datasets under the camouflaged object segmentation task?","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":2,"papers_with_code":2,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"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":2,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/camouflaged-object-segmentation-with-a-single-1","slug":"camouflaged-object-segmentation-with-a-single-1","dataset":"CAMO","dataset_url":"/dataset/camo","rows_in_archive":3,"metrics":["E_{\\phi}","F_{\\beta}","MAE","S_{\\alpha}"],"first_row_in_archive_order":{"model":"RDVP-MSD","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/camouflaged-object-segmentation-with-a-single-2","slug":"camouflaged-object-segmentation-with-a-single-2","dataset":"COD10K","dataset_url":"/dataset/cod10k","rows_in_archive":3,"metrics":["E_{\\phi}","F_{\\beta}","MAE","S_{\\alpha}"],"first_row_in_archive_order":{"model":"RDVP-MSD","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/camouflaged-object-segmentation-with-a-single","slug":"camouflaged-object-segmentation-with-a-single","dataset":"Chameleon","dataset_url":null,"rows_in_archive":2,"metrics":["E_{\\phi}","F_{\\beta}","MAE","S_{\\alpha}"],"first_row_in_archive_order":{"model":"ProMaC","paper_title":"Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentation","paper_url":"/paper/leveraging-hallucinations-to-reduce-manual","paper_date":"2024-08-27","arxiv_id":"2408.15205","code_links":[{"title":"lwpyh/ProMaC_code","url":"https://github.com/lwpyh/ProMaC_code"}],"syntology":{"n":9,"n_ran":2,"n_unverified":7,"n_pointer_only":0}}}],"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}],"subtasks":[],"parent_tasks":[{"url":"/task/camouflaged-object-segmentation","name":"Camouflaged 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":2,"of":2,"tagged_in_all":2,"items":[{"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/relax-image-specific-prompt-requirement-in","title":"Relax Image-Specific Prompt Requirement in SAM: A Single Generic Prompt for Segmenting Camouflaged Objects","date":"2023-12-12","arxiv_id":"2312.07374","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_unverified":5,"n_pointer_only":0}}],"syntology_records":2,"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":"2026-09-24T18:15:14+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"}}