{"url":"/dataset/mas3k","name":"MAS3K","full_name":"MAS3K: An Open Dataset for Marine Animal Segmentation","description_markdown":"MAS3K contains a total of 3,103 images, where 1,588 are for camouflaged cases, 1,322 are for common cases, and 193 are underwater images in absence of marine animals. The marine animal categories in MAS3K cover both vertebrate and invertebrate, including seven super-classes, e.g., mammals, reptile, arthropod, and marine fish, etc. Under the super-classes, MAS3K dataset has 37 sub-classes, e.g., crab, starfish, shark, and turtle, etc.","description_withheld":null,"homepage":"https://github.com/LinLi-DL/MAS","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Image Segmentation","url":"/task/image-segmentation","datasets_with_task":"/datasets/task/image-segmentation"},{"name":"Marine Animal Segmentation","url":"/task/marine-animal-segmentation","datasets_with_task":"/datasets/task/marine-animal-segmentation"}],"languages":[],"variants":["MAS3K"],"data_loaders":[{"repo":"https://github.com/drchip61/mas-sam","url":"https://github.com/drchip61/mas-sam","frameworks":["pytorch"]},{"repo":"https://github.com/LinLi-DL/MAS","url":"https://github.com/LinLi-DL/MAS","frameworks":["pytorch"]}],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-segmentation-on-mas3k","task":"Image Segmentation","dataset_variant":"MAS3K","rows":4,"metrics":["mIoU","S-measure","E-measure","MAE"],"first_row_in_archive_order":{"model":"SAM2-UNet","paper":"/paper/sam2-unet-segment-anything-2-makes-strong","metrics":{"E-measure":"0.943","MAE":"0.021","S-measure":"0.903","mIoU":"0.799"},"code_links":[{"title":"wzh0120/sam2-unet","url":"https://github.com/wzh0120/sam2-unet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/sam2-unet-segment-anything-2-makes-strong","title":"SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation","date":"2024-08-16","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":5,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mas-sam-segment-any-marine-animal-with","title":"MAS-SAM: Segment Any Marine Animal with Aggregated Features","date":"2024-04-24","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":20,"samples_ran":12,"samples_unverified":8,"pointer_only_for_licence":20,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/masnet-a-robust-deep-marine-animal","title":"MASNet: A Robust Deep Marine Animal Segmentation Network","date":"2023-05-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/zoom-in-and-out-a-mixed-scale-triplet-network","title":"Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection","date":"2022-03-05","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":12,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":42,"samples_ran":29,"samples_unverified":13,"pointer_only_for_licence":20,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}