{"url":"/task/universal-segmentation","name":"Universal Segmentation","slug":"universal-segmentation","description_markdown":"Universal segmentation is a challenging computer vision task that aims to segment images into semantic regions, regardless of the task or the domain. It requires the model to learn a wide range of visual concepts and to be able to generalize to new tasks and domains.","categories":[{"name":"Computer Code","url":"/area/computer-code"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Medical","url":"/area/medical"},{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":32,"papers_with_code":25,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/semantic-segmentation","name":"Semantic 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":25,"of":25,"tagged_in_all":32,"items":[{"url":"/paper/masked-attention-mask-transformer-for","title":"Masked-attention Mask Transformer for Universal Image Segmentation","date":"2021-12-02","arxiv_id":"2112.01527","repositories_listed":7,"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/oneformer-one-transformer-to-rule-universal","title":"OneFormer: One Transformer to Rule Universal Image Segmentation","date":"2022-11-10","arxiv_id":"2211.06220","repositories_listed":4,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/rethinking-the-evaluation-of-visible-and","title":"Rethinking the Evaluation of Visible and Infrared Image Fusion","date":"2024-10-09","arxiv_id":"2410.06811","repositories_listed":3,"syntology":null},{"url":"/paper/segment-everything-everywhere-all-at-once","title":"Segment Everything Everywhere All at Once","date":"2023-04-13","arxiv_id":"2304.06718","repositories_listed":3,"syntology":null},{"url":"/paper/unsupervised-universal-image-segmentation","title":"Unsupervised Universal Image Segmentation","date":"2023-12-28","arxiv_id":"2312.17243","repositories_listed":2,"syntology":{"n":15,"n_ran":13,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/one-model-to-rule-them-all-towards-universal","title":"One Model to Rule them All: Towards Universal Segmentation for Medical Images with Text Prompts","date":"2023-12-28","arxiv_id":"2312.17183","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/universal-segmentation-at-arbitrary","title":"Universal Segmentation at Arbitrary Granularity with Language Instruction","date":"2023-12-04","arxiv_id":"2312.01623","repositories_listed":2,"syntology":{"n":16,"n_ran":13,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/the-missing-point-in-vision-transformers-for","title":"The Missing Point in Vision Transformers for Universal Image Segmentation","date":"2025-05-26","arxiv_id":"2505.19795","repositories_listed":1,"syntology":null},{"url":"/paper/semisam-rethinking-semi-supervised-medical","title":"SemiSAM+: Rethinking Semi-Supervised Medical Image Segmentation in the Era of Foundation Models","date":"2025-02-28","arxiv_id":"2502.20749","repositories_listed":1,"syntology":null},{"url":"/paper/seganypet-universal-promptable-segmentation","title":"SegAnyPET: Universal Promptable Segmentation from Positron Emission Tomography Images","date":"2025-02-20","arxiv_id":"2502.14351","repositories_listed":1,"syntology":null},{"url":"/paper/medicosam-towards-foundation-models-for","title":"MedicoSAM: Towards foundation models for medical image segmentation","date":"2025-01-20","arxiv_id":"2501.11734","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/voila-complexity-aware-universal-segmentation","title":"VOILA: Complexity-Aware Universal Segmentation of CT images by Voxel Interacting with Language","date":"2025-01-07","arxiv_id":"2501.03482","repositories_listed":1,"syntology":null},{"url":"/paper/hyperseg-hybrid-segmentation-assistant-with","title":"HyperSeg: Hybrid Segmentation Assistant with Fine-grained Visual Perceiver","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/instructseg-unifying-instructed-visual","title":"InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models","date":"2024-12-18","arxiv_id":"2412.14006","repositories_listed":1,"syntology":{"n":14,"n_ran":6,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/hyperseg-towards-universal-visual","title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","date":"2024-11-26","arxiv_id":"2411.17606","repositories_listed":1,"syntology":{"n":17,"n_ran":7,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/large-language-model-with-region-guided","title":"Large Language Model with Region-guided Referring and Grounding for CT Report Generation","date":"2024-11-23","arxiv_id":"2411.15539","repositories_listed":1,"syntology":null},{"url":"/paper/meduniseg-2d-and-3d-medical-image","title":"MedUniSeg: 2D and 3D Medical Image Segmentation via a Prompt-driven Universal Model","date":"2024-10-08","arxiv_id":"2410.05905","repositories_listed":1,"syntology":null},{"url":"/paper/omg-llava-bridging-image-level-object-level","title":"OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding","date":"2024-06-27","arxiv_id":"2406.19389","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":4}},{"url":"/paper/radgenome-chest-ct-a-grounded-vision-language","title":"RadGenome-Chest CT: A Grounded Vision-Language Dataset for Chest CT Analysis","date":"2024-04-25","arxiv_id":"2404.16754","repositories_listed":1,"syntology":null},{"url":"/paper/progressive-token-length-scaling-in","title":"Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation","date":"2024-04-23","arxiv_id":"2404.14657","repositories_listed":1,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":7}},{"url":"/paper/hierarchical-open-vocabulary-universal-image-1","title":"Hierarchical Open-vocabulary Universal Image Segmentation","date":"2023-07-03","arxiv_id":"2307.00764","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/clustseg-clustering-for-universal","title":"CLUSTSEG: Clustering for Universal Segmentation","date":"2023-05-03","arxiv_id":"2305.02187","repositories_listed":1,"syntology":null},{"url":"/paper/uniseg-a-prompt-driven-universal-segmentation","title":"UniSeg: A Prompt-driven Universal Segmentation Model as well as A Strong Representation Learner","date":"2023-04-07","arxiv_id":"2304.03493","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/training-a-universal-instance-segmentation","title":"Training a universal instance segmentation network for live cell images of various cell types and imaging modalities","date":"2022-07-28","arxiv_id":"2207.14347","repositories_listed":1,"syntology":null}],"syntology_records":11,"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"}}