{"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/unsupervised-universal-image-segmentation","title":"Unsupervised Universal Image Segmentation","arxiv_id":"2312.17243","date":"2023-12-28","proceeding":"CVPR 2024 1","authors":["Dantong Niu","Xudong Wang","Xinyang Han","Long Lian","Roei Herzig","Trevor Darrell"],"abstract":"Several unsupervised image segmentation approaches have been proposed which eliminate the need for dense manually-annotated segmentation masks; current models separately handle either semantic segmentation (e.g., STEGO) or class-agnostic instance segmentation (e.g., CutLER), but not both (i.e., panoptic segmentation). We propose an Unsupervised Universal Segmentation model (U2Seg) adept at performing various image segmentation tasks -- instance, semantic and panoptic -- using a novel unified framework. U2Seg generates pseudo semantic labels for these segmentation tasks via leveraging self-supervised models followed by clustering; each cluster represents different semantic and/or instance membership of pixels. We then self-train the model on these pseudo semantic labels, yielding substantial performance gains over specialized methods tailored to each task: a +2.6 AP$^{\\text{box}}$ boost vs. CutLER in unsupervised instance segmentation on COCO and a +7.0 PixelAcc increase (vs. STEGO) in unsupervised semantic segmentation on COCOStuff. Moreover, our method sets up a new baseline for unsupervised panoptic segmentation, which has not been previously explored. U2Seg is also a strong pretrained model for few-shot segmentation, surpassing CutLER by +5.0 AP$^{\\text{mask}}$ when trained on a low-data regime, e.g., only 1% COCO labels. We hope our simple yet effective method can inspire more research on unsupervised universal image segmentation.","url_abs":"https://arxiv.org/abs/2312.17243v1","url_pdf":"https://arxiv.org/pdf/2312.17243v1.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":"unsupervised-universal-image-segmentation","repo_url":"https://github.com/u2seg/u2seg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"unsupervised-universal-image-segmentation","repo_url":"https://github.com/dantong88/llarva","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"universal-segmentation","task_name":"Universal Segmentation"},{"task_slug":"unsupervised-image-segmentation","task_name":"Unsupervised Image Segmentation"},{"task_slug":"unsupervised-instance-segmentation","task_name":"Unsupervised Instance Segmentation"},{"task_slug":"unsupervised-panoptic-segmentation","task_name":"Unsupervised Panoptic Segmentation"},{"task_slug":"unsupervised-semantic-segmentation","task_name":"Unsupervised Semantic Segmentation"},{"task_slug":"unsupervised-zero-shot-instance-segmentation","task_name":"Unsupervised Zero-Shot Instance Segmentation"},{"task_slug":"unsupervised-zero-shot-panoptic-segmentation","task_name":"Unsupervised Zero-Shot Panoptic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-panoptic-segmentation-on-bdd100k","task":"Unsupervised Panoptic Segmentation","dataset":"BDD100K val","model":"U2Seg","rank_in_archive_order":4,"of":4,"metrics":{"PQ":"15.8"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-panoptic-segmentation-on-coco","task":"Unsupervised Panoptic Segmentation","dataset":"COCO val2017","model":"U2Seg","rank_in_archive_order":1,"of":2,"metrics":{"PQ":"16.1","RQ":"19.9","SQ":"71.1"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-panoptic-segmentation-on","task":"Unsupervised Panoptic Segmentation","dataset":"Cityscapes","model":"U2Seg (827 pseudo-classes)","rank_in_archive_order":4,"of":5,"metrics":{"PQ":"18.4"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-panoptic-segmentation-on-kitti","task":"Unsupervised Panoptic Segmentation","dataset":"KITTI","model":"U2Seg","rank_in_archive_order":4,"of":4,"metrics":{"PQ":"20.6"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-panoptic-segmentation-on-muses","task":"Unsupervised Panoptic Segmentation","dataset":"MUSES: MUlti-SEnsor Semantic perception dataset","model":"U2Seg","rank_in_archive_order":4,"of":4,"metrics":{"PQ":"20.3"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-panoptic-segmentation-on-waymo","task":"Unsupervised Panoptic Segmentation","dataset":"Waymo Open Dataset","model":"U2Seg","rank_in_archive_order":4,"of":4,"metrics":{"PQ":"19.8"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-on-coco-7","task":"Unsupervised Semantic Segmentation","dataset":"COCO-Stuff-27","model":"U2Seg","rank_in_archive_order":5,"of":29,"metrics":{"Clustering [Accuracy]":"63.9","Clustering [mIoU]":"30.2"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-zero-shot-instance-segmentation","task":"Unsupervised Zero-Shot Instance Segmentation","dataset":"COCO val2017","model":"U2Seg","rank_in_archive_order":1,"of":2,"metrics":{"AP":"6.4","AP50":"11.2","AP75":"6.4","AR100":"18.5"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-zero-shot-panoptic-segmentation","task":"Unsupervised Zero-Shot Panoptic Segmentation","dataset":"COCO val2017","model":"U2Seg","rank_in_archive_order":1,"of":1,"metrics":{"PQ":"11.1","RQ":"13.7","SQ":"60.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.17243","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17243"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/dantong88/llarva","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/u2seg/u2seg","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":3,"ran":6,"ran_fixture":4,"unverified":2},"by_repo_kind":{"official":{"samples":8,"ran":6,"repositories":1},"listed":{"samples":7,"ran":7,"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":"20e4f665698a3d18","entry":"collate_fn","repo":"dantong88/llarva","repo_kind":"listed","path":"llava/eval/model_vqa_loader.py","file_url":"https://github.com/dantong88/llarva/blob/HEAD/llava/eval/model_vqa_loader.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"20e4f665698a3d18"}},{"code_sha256_prefix":"fb569f13818701fc","entry":"conv","repo":"u2seg/u2seg","repo_kind":"official","path":"u2seg/Instance_Clustering/semisup-simclrv2/resnet.py","file_url":"https://github.com/u2seg/u2seg/blob/HEAD/u2seg/Instance_Clustering/semisup-simclrv2/resnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fb569f13818701fc"}},{"code_sha256_prefix":"7e03b180fa317c9a","entry":"divide_to_patches","repo":"dantong88/llarva","repo_kind":"listed","path":"llava/mm_utils.py","file_url":"https://github.com/dantong88/llarva/blob/HEAD/llava/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7e03b180fa317c9a"}},{"code_sha256_prefix":"55120f2026b56aa2","entry":"drop_path","repo":"u2seg/u2seg","repo_kind":"official","path":"u2seg/Instance_Clustering/selective_labeling/dino.py","file_url":"https://github.com/u2seg/u2seg/blob/HEAD/u2seg/Instance_Clustering/selective_labeling/dino.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"code_sha256_prefix":"23374018ab9941b5","entry":"evaluate_predictions","repo":"u2seg/u2seg","repo_kind":"official","path":"u2seg/Instance_Clustering/usl-t_pretraining/usl-t-imagenet-pretrain.py","file_url":"https://github.com/u2seg/u2seg/blob/HEAD/u2seg/Instance_Clustering/usl-t_pretraining/usl-t-imagenet-pretrain.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"23374018ab9941b5"}},{"code_sha256_prefix":"42a46570620cd9fa","entry":"get_chunk","repo":"dantong88/llarva","repo_kind":"listed","path":"llava/eval/model_vqa.py","file_url":"https://github.com/dantong88/llarva/blob/HEAD/llava/eval/model_vqa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"42a46570620cd9fa"}},{"code_sha256_prefix":"0e80e018f0e62f7b","entry":"name_to_params","repo":"u2seg/u2seg","repo_kind":"official","path":"u2seg/Instance_Clustering/semisup-simclrv2/resnet.py","file_url":"https://github.com/u2seg/u2seg/blob/HEAD/u2seg/Instance_Clustering/semisup-simclrv2/resnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0e80e018f0e62f7b"}},{"code_sha256_prefix":"468eedeba67f1b00","entry":"resize_and_pad_image","repo":"dantong88/llarva","repo_kind":"listed","path":"llava/mm_utils.py","file_url":"https://github.com/dantong88/llarva/blob/HEAD/llava/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"468eedeba67f1b00"}},{"code_sha256_prefix":"3999ff487573f32c","entry":"select_best_resolution","repo":"dantong88/llarva","repo_kind":"listed","path":"llava/mm_utils.py","file_url":"https://github.com/dantong88/llarva/blob/HEAD/llava/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3999ff487573f32c"}},{"code_sha256_prefix":"076c252c52cbb161","entry":"split_list","repo":"dantong88/llarva","repo_kind":"listed","path":"llava/eval/model_vqa.py","file_url":"https://github.com/dantong88/llarva/blob/HEAD/llava/eval/model_vqa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"076c252c52cbb161"}},{"code_sha256_prefix":"0f0abfb396e03541","entry":"test_opencv_video_format","repo":"u2seg/u2seg","repo_kind":"official","path":"demo/u2seg_demo.py","file_url":"https://github.com/u2seg/u2seg/blob/HEAD/demo/u2seg_demo.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0f0abfb396e03541"}},{"code_sha256_prefix":"915b71e73a54fc97","entry":"trunc_normal_","repo":"u2seg/u2seg","repo_kind":"official","path":"u2seg/Instance_Clustering/selective_labeling/dino.py","file_url":"https://github.com/u2seg/u2seg/blob/HEAD/u2seg/Instance_Clustering/selective_labeling/dino.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"915b71e73a54fc97"}},{"code_sha256_prefix":"55c32993da87759b","entry":"unpad_image","repo":"dantong88/llarva","repo_kind":"listed","path":"llava/model/llava_arch.py","file_url":"https://github.com/dantong88/llarva/blob/HEAD/llava/model/llava_arch.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"55c32993da87759b"}},{"code_sha256_prefix":"1f977428f41dd1e0","entry":"get_resnet","repo":"u2seg/u2seg","repo_kind":"official","path":"u2seg/Instance_Clustering/semisup-simclrv2/resnet.py","file_url":"https://github.com/u2seg/u2seg/blob/HEAD/u2seg/Instance_Clustering/semisup-simclrv2/resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1f977428f41dd1e0"}},{"code_sha256_prefix":"c2eb0fe4668d4549","entry":"vit_small","repo":"u2seg/u2seg","repo_kind":"official","path":"u2seg/Instance_Clustering/selective_labeling/dino.py","file_url":"https://github.com/u2seg/u2seg/blob/HEAD/u2seg/Instance_Clustering/selective_labeling/dino.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c2eb0fe4668d4549"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}