{"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/croc-cross-view-online-clustering-for-dense","title":"CrOC: Cross-View Online Clustering for Dense Visual Representation Learning","arxiv_id":"2303.13245","date":"2023-03-23","proceeding":"CVPR 2023 1","authors":["Thomas Stegmüller","Tim Lebailly","Behzad Bozorgtabar","Tinne Tuytelaars","Jean-Philippe Thiran"],"abstract":"Learning dense visual representations without labels is an arduous task and more so from scene-centric data. We propose to tackle this challenging problem by proposing a Cross-view consistency objective with an Online Clustering mechanism (CrOC) to discover and segment the semantics of the views. In the absence of hand-crafted priors, the resulting method is more generalizable and does not require a cumbersome pre-processing step. More importantly, the clustering algorithm conjointly operates on the features of both views, thereby elegantly bypassing the issue of content not represented in both views and the ambiguous matching of objects from one crop to the other. We demonstrate excellent performance on linear and unsupervised segmentation transfer tasks on various datasets and similarly for video object segmentation. Our code and pre-trained models are publicly available at https://github.com/stegmuel/CrOC.","url_abs":"https://arxiv.org/abs/2303.13245v1","url_pdf":"https://arxiv.org/pdf/2303.13245v1.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":"croc-cross-view-online-clustering-for-dense","repo_url":"https://github.com/stegmuel/croc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"croc-cross-view-online-clustering-for-dense","repo_url":"https://github.com/tileb1/adasim","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"online-clustering","task_name":"Online Clustering"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-semantic-segmentation","task_name":"Unsupervised Semantic Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-semantic-segmentation-on-coco-7","task":"Unsupervised Semantic Segmentation","dataset":"COCO-Stuff-27","model":"CrOC (ViT-S/16, COCO+)","rank_in_archive_order":19,"of":29,"metrics":{"Clustering [mIoU]":"21.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.13245","atlas_url":"https://app.syntology.ai/?focus=2303.13245","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13245"}},"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/tileb1/adasim","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stegmuel/croc","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/stegmuel/CrOC","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_honours":1,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"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":"4d25be8ebf17fde1","entry":"bool_flag","repo":"stegmuel/CrOC","repo_kind":"official","path":"croc_utils/parser.py","file_url":"https://github.com/stegmuel/CrOC/blob/HEAD/croc_utils/parser.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4d25be8ebf17fde1"}},{"code_sha256_prefix":"2b5489053b222e00","entry":"clip_gradients","repo":"stegmuel/CrOC","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/stegmuel/CrOC/blob/HEAD/utils/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2b5489053b222e00"}},{"code_sha256_prefix":"cafeca699418ba7b","entry":"collate_fn","repo":"stegmuel/CrOC","repo_kind":"official","path":"croc_utils/datasets.py","file_url":"https://github.com/stegmuel/CrOC/blob/HEAD/croc_utils/datasets.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cafeca699418ba7b"}},{"code_sha256_prefix":"361a6b24f11fc50a","entry":"cosine_scheduler","repo":"stegmuel/CrOC","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/stegmuel/CrOC/blob/HEAD/utils/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"361a6b24f11fc50a"}},{"code_sha256_prefix":"55120f2026b56aa2","entry":"drop_path","repo":"stegmuel/CrOC","repo_kind":"official","path":"models/vision_transformer.py","file_url":"https://github.com/stegmuel/CrOC/blob/HEAD/models/vision_transformer.py","link_basis":"harvester_set","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":"55120f2026b56aa2"}},{"code_sha256_prefix":"614a514e2a5fd725","entry":"get_tensor_binary_instance_labels","repo":"stegmuel/CrOC","repo_kind":"official","path":"croc_utils/datasets.py","file_url":"https://github.com/stegmuel/CrOC/blob/HEAD/croc_utils/datasets.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"614a514e2a5fd725"}},{"code_sha256_prefix":"beef3584d62ffde9","entry":"get_dataset","repo":"stegmuel/CrOC","repo_kind":"official","path":"croc_utils/datasets.py","file_url":"https://github.com/stegmuel/CrOC/blob/HEAD/croc_utils/datasets.py","link_basis":"harvester_set","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":"beef3584d62ffde9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}