{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/hierarchical-open-vocabulary-universal-image-1","title":"Hierarchical Open-vocabulary Universal Image Segmentation","arxiv_id":"2307.00764","date":"2023-07-03","proceeding":"NeurIPS 2023 11","authors":["Xudong Wang","Shufan Li","Konstantinos Kallidromitis","Yusuke Kato","Kazuki Kozuka","Trevor Darrell"],"abstract":"Open-vocabulary image segmentation aims to partition an image into semantic regions according to arbitrary text descriptions. However, complex visual scenes can be naturally decomposed into simpler parts and abstracted at multiple levels of granularity, introducing inherent segmentation ambiguity. Unlike existing methods that typically sidestep this ambiguity and treat it as an external factor, our approach actively incorporates a hierarchical representation encompassing different semantic-levels into the learning process. We propose a decoupled text-image fusion mechanism and representation learning modules for both \"things\" and \"stuff\". Additionally, we systematically examine the differences that exist in the textual and visual features between these types of categories. Our resulting model, named HIPIE, tackles HIerarchical, oPen-vocabulary, and unIvErsal segmentation tasks within a unified framework. Benchmarked on over 40 datasets, e.g., ADE20K, COCO, Pascal-VOC Part, RefCOCO/RefCOCOg, ODinW and SeginW, HIPIE achieves the state-of-the-art results at various levels of image comprehension, including semantic-level (e.g., semantic segmentation), instance-level (e.g., panoptic/referring segmentation and object detection), as well as part-level (e.g., part/subpart segmentation) tasks. Our code is released at https://github.com/berkeley-hipie/HIPIE.","url_abs":"https://arxiv.org/abs/2307.00764v2","url_pdf":"https://arxiv.org/pdf/2307.00764v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"hierarchical-open-vocabulary-universal-image-1","repo_url":"https://github.com/berkeley-hipie/hipie","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-comprehension","task_name":"Image Comprehension"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"universal-segmentation","task_name":"Universal Segmentation"},{"task_slug":"zero-shot-segmentation","task_name":"Zero Shot Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-segmentation-on-pascal-panoptic-parts","task":"Image Segmentation","dataset":"Pascal Panoptic Parts","model":"HIPIE (ViT-H)","rank_in_archive_order":1,"of":4,"metrics":{"mIoUPartS":"63.8"},"uses_additional_data":false},{"leaderboard":"/sota/image-segmentation-on-pascal-panoptic-parts","task":"Image Segmentation","dataset":"Pascal Panoptic Parts","model":"HIPIE (ResNet-50)","rank_in_archive_order":3,"of":4,"metrics":{"mIoUPartS":"57.2"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-coco-minival","task":"Panoptic Segmentation","dataset":"COCO minival","model":"HIPIE (ViT-H, single-scale)","rank_in_archive_order":12,"of":31,"metrics":{"PQ":"58.1","mIoU":"66.8"},"uses_additional_data":true},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-3","task":"Referring Expression Segmentation","dataset":"RefCOCO+ val","model":"HIPIE","rank_in_archive_order":7,"of":33,"metrics":{"Overall IoU":"73.9"},"uses_additional_data":true},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco","task":"Referring Expression Segmentation","dataset":"RefCoCo val","model":"HIPIE","rank_in_archive_order":5,"of":37,"metrics":{"Overall IoU":"82.8"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-segmentation-on-segmentation-in-the","task":"Zero Shot Segmentation","dataset":"Segmentation in the Wild","model":"HIPIE","rank_in_archive_order":4,"of":12,"metrics":{"Mean AP":"41.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2307.00764","atlas_url":"https://app.syntology.ai/?focus=2307.00764","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.00764"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/berkeley-hipie/hipie","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":2,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"3a4a70eddd103b6f","entry":"get_images_color_similarity","repo":"berkeley-hipie/hipie","repo_kind":"official","path":"projects/HIPIE/hipie/hipie_img.py","file_url":"https://github.com/berkeley-hipie/hipie/blob/HEAD/projects/HIPIE/hipie/hipie_img.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3a4a70eddd103b6f"}},{"code_sha256_prefix":"6bc62d34967e2917","entry":"unfold_wo_center","repo":"berkeley-hipie/hipie","repo_kind":"official","path":"projects/HIPIE/hipie/hipie_img.py","file_url":"https://github.com/berkeley-hipie/hipie/blob/HEAD/projects/HIPIE/hipie/hipie_img.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6bc62d34967e2917"}},{"code_sha256_prefix":"133372f6b12b6ba0","entry":"convert_grounding_to_od_logits","repo":"berkeley-hipie/hipie","repo_kind":"official","path":"projects/HIPIE/hipie/hipie_img.py","file_url":"https://github.com/berkeley-hipie/hipie/blob/HEAD/projects/HIPIE/hipie/hipie_img.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"133372f6b12b6ba0"}},{"code_sha256_prefix":"0d78867cbc2d1619","entry":"vote","repo":"berkeley-hipie/hipie","repo_kind":"official","path":"projects/HIPIE/hipie/demo_lib/demo_utils.py","file_url":"https://github.com/berkeley-hipie/hipie/blob/HEAD/projects/HIPIE/hipie/demo_lib/demo_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0d78867cbc2d1619"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}