{"url":"/task/open-vocabulary-panoptic-segmentation","name":"Open Vocabulary Panoptic Segmentation","slug":"open-vocabulary-panoptic-segmentation","description_markdown":null,"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":17,"papers_with_code":12,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":1,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/open-vocabulary-panoptic-segmentation-on","slug":"open-vocabulary-panoptic-segmentation-on","dataset":"ADE20K","dataset_url":"/dataset/ade20k","rows_in_archive":10,"metrics":["PQ"],"first_row_in_archive_order":{"model":"UMG-CLIP-E/14","paper_title":"UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding","paper_url":"/paper/umg-clip-a-unified-multi-granularity-vision","paper_date":"2024-01-12","arxiv_id":"2401.06397","code_links":[{"title":"lygsbw/umg-clip","url":"https://github.com/lygsbw/umg-clip"}],"syntology":null}}],"datasets":[{"url":"/dataset/ade20k","name":"ADE20K","full_name":"","num_papers_in_archive":1213}],"subtasks":[],"parent_tasks":[],"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":12,"of":12,"tagged_in_all":17,"items":[{"url":"/paper/panoptic-vision-language-feature-fields","title":"Panoptic Vision-Language Feature Fields","date":"2023-09-11","arxiv_id":"2309.05448","repositories_listed":2,"syntology":null},{"url":"/paper/openseg-r-improving-open-vocabulary","title":"OpenSeg-R: Improving Open-Vocabulary Segmentation via Step-by-Step Visual Reasoning","date":"2025-05-22","arxiv_id":"2505.16974","repositories_listed":1,"syntology":null},{"url":"/paper/open-vocabulary-panoptic-segmentation-using","title":"Open-Vocabulary Panoptic Segmentation Using BERT Pre-Training of Vision-Language Multiway Transformer Model","date":"2024-12-25","arxiv_id":"2412.18917","repositories_listed":1,"syntology":null},{"url":"/paper/eov-seg-efficient-open-vocabulary-panoptic","title":"EOV-Seg: Efficient Open-Vocabulary Panoptic Segmentation","date":"2024-12-11","arxiv_id":"2412.08628","repositories_listed":1,"syntology":null},{"url":"/paper/collaborative-vision-text-representation","title":"Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation","date":"2024-08-01","arxiv_id":"2408.00744","repositories_listed":1,"syntology":null},{"url":"/paper/possam-panoptic-open-vocabulary-segment-1","title":"PosSAM: Panoptic Open-vocabulary Segment Anything","date":"2024-03-14","arxiv_id":"2403.09620","repositories_listed":1,"syntology":null},{"url":"/paper/umg-clip-a-unified-multi-granularity-vision","title":"UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding","date":"2024-01-12","arxiv_id":"2401.06397","repositories_listed":1,"syntology":null},{"url":"/paper/clipself-vision-transformer-distills-itself","title":"CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction","date":"2023-10-02","arxiv_id":"2310.01403","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":6}},{"url":"/paper/convolutions-die-hard-open-vocabulary-1","title":"Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP","date":"2023-08-04","arxiv_id":"2308.02487","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/open-vocabulary-panoptic-segmentation-with-1","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","date":"2023-03-08","arxiv_id":"2303.04803","repositories_listed":1,"syntology":null},{"url":"/paper/open-vocabulary-panoptic-segmentation-with","title":"Open-Vocabulary Universal Image Segmentation with MaskCLIP","date":"2022-08-18","arxiv_id":"2208.08984","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/denseclip-extract-free-dense-labels-from-clip","title":"Extract Free Dense Labels from CLIP","date":"2021-12-02","arxiv_id":"2112.01071","repositories_listed":1,"syntology":null}],"syntology_records":3,"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"}}