{"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/p-2-ot-progressive-partial-optimal-transport","title":"P$^2$OT: Progressive Partial Optimal Transport for Deep Imbalanced Clustering","arxiv_id":"2401.09266","date":"2024-01-17","proceeding":null,"authors":["Chuyu Zhang","Hui Ren","Xuming He"],"abstract":"Deep clustering, which learns representation and semantic clustering without labels information, poses a great challenge for deep learning-based approaches. Despite significant progress in recent years, most existing methods focus on uniformly distributed datasets, significantly limiting the practical applicability of their methods. In this paper, we first introduce a more practical problem setting named deep imbalanced clustering, where the underlying classes exhibit an imbalance distribution. To tackle this problem, we propose a novel pseudo-labeling-based learning framework. Our framework formulates pseudo-label generation as a progressive partial optimal transport problem, which progressively transports each sample to imbalanced clusters under prior distribution constraints, thus generating imbalance-aware pseudo-labels and learning from high-confident samples. In addition, we transform the initial formulation into an unbalanced optimal transport problem with augmented constraints, which can be solved efficiently by a fast matrix scaling algorithm. Experiments on various datasets, including a human-curated long-tailed CIFAR100, challenging ImageNet-R, and large-scale subsets of fine-grained iNaturalist2018 datasets, demonstrate the superiority of our method.","url_abs":"https://arxiv.org/abs/2401.09266v1","url_pdf":"https://arxiv.org/pdf/2401.09266v1.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":"p-2-ot-progressive-partial-optimal-transport","repo_url":"https://github.com/rhfeiyang/ppot","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"deep-clustering","task_name":"Deep Clustering"},{"task_slug":"pseudo-label","task_name":"Pseudo Label"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.09266","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09266"}},"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/rhfeiyang/ppot","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_honours":2,"ran":6,"unverified":2},"by_repo_kind":{"official":{"samples":10,"ran":8,"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":10,"samples":[{"code_sha256_prefix":"3fb68ed6809a8085","entry":"sigmoid_rampup","repo":"rhfeiyang/ppot","repo_kind":"official","path":"losses/ramps.py","file_url":"https://github.com/rhfeiyang/ppot/blob/HEAD/losses/ramps.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3fb68ed6809a8085"}},{"code_sha256_prefix":"d003b47d8f4e4a87","entry":"classify","repo":"rhfeiyang/ppot","repo_kind":"official","path":"models/classifer.py","file_url":"https://github.com/rhfeiyang/ppot/blob/HEAD/models/classifer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d003b47d8f4e4a87"}},{"code_sha256_prefix":"214e4ee9afcfa0e3","entry":"cosine_rampdown","repo":"rhfeiyang/ppot","repo_kind":"official","path":"losses/ramps.py","file_url":"https://github.com/rhfeiyang/ppot/blob/HEAD/losses/ramps.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"214e4ee9afcfa0e3"}},{"code_sha256_prefix":"2fc1613bdc5af72d","entry":"get_model","repo":"rhfeiyang/ppot","repo_kind":"official","path":"utils/common_config.py","file_url":"https://github.com/rhfeiyang/ppot/blob/HEAD/utils/common_config.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"2fc1613bdc5af72d"}},{"code_sha256_prefix":"8c20a94acbebafc2","entry":"get_parameter_with_grad","repo":"rhfeiyang/ppot","repo_kind":"official","path":"models/dino.py","file_url":"https://github.com/rhfeiyang/ppot/blob/HEAD/models/dino.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8c20a94acbebafc2"}},{"code_sha256_prefix":"3994cc6d965fb124","entry":"get_predictions","repo":"rhfeiyang/ppot","repo_kind":"official","path":"utils/evaluate_utils.py","file_url":"https://github.com/rhfeiyang/ppot/blob/HEAD/utils/evaluate_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"3994cc6d965fb124"}},{"code_sha256_prefix":"3dd636cbaa579436","entry":"get_train_dataset","repo":"rhfeiyang/ppot","repo_kind":"official","path":"utils/common_config.py","file_url":"https://github.com/rhfeiyang/ppot/blob/HEAD/utils/common_config.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"3dd636cbaa579436"}},{"code_sha256_prefix":"6768b5d32c13e48d","entry":"get_val_dataset","repo":"rhfeiyang/ppot","repo_kind":"official","path":"utils/common_config.py","file_url":"https://github.com/rhfeiyang/ppot/blob/HEAD/utils/common_config.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"6768b5d32c13e48d"}},{"code_sha256_prefix":"926ad512c561d413","entry":"get_dino_vitb16","repo":"rhfeiyang/ppot","repo_kind":"official","path":"models/dino.py","file_url":"https://github.com/rhfeiyang/ppot/blob/HEAD/models/dino.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"926ad512c561d413"}},{"code_sha256_prefix":"069122bd5268cc56","entry":"linear_rampup","repo":"rhfeiyang/ppot","repo_kind":"official","path":"losses/ramps.py","file_url":"https://github.com/rhfeiyang/ppot/blob/HEAD/losses/ramps.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"069122bd5268cc56"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}