{"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/large-scale-pre-training-for-person-re","title":"Large-Scale Pre-training for Person Re-identification with Noisy Labels","arxiv_id":"2203.16533","date":"2022-03-30","proceeding":"CVPR 2022 1","authors":["Dengpan Fu","Dongdong Chen","Hao Yang","Jianmin Bao","Lu Yuan","Lei Zhang","Houqiang Li","Fang Wen","Dong Chen"],"abstract":"This paper aims to address the problem of pre-training for person re-identification (Re-ID) with noisy labels. To setup the pre-training task, we apply a simple online multi-object tracking system on raw videos of an existing unlabeled Re-ID dataset \"LUPerson\" nd build the Noisy Labeled variant called \"LUPerson-NL\". Since theses ID labels automatically derived from tracklets inevitably contain noises, we develop a large-scale Pre-training framework utilizing Noisy Labels (PNL), which consists of three learning modules: supervised Re-ID learning, prototype-based contrastive learning, and label-guided contrastive learning. In principle, joint learning of these three modules not only clusters similar examples to one prototype, but also rectifies noisy labels based on the prototype assignment. We demonstrate that learning directly from raw videos is a promising alternative for pre-training, which utilizes spatial and temporal correlations as weak supervision. This simple pre-training task provides a scalable way to learn SOTA Re-ID representations from scratch on \"LUPerson-NL\" without bells and whistles. For example, by applying on the same supervised Re-ID method MGN, our pre-trained model improves the mAP over the unsupervised pre-training counterpart by 5.7%, 2.2%, 2.3% on CUHK03, DukeMTMC, and MSMT17 respectively. Under the small-scale or few-shot setting, the performance gain is even more significant, suggesting a better transferability of the learned representation. Code is available at https://github.com/DengpanFu/LUPerson-NL","url_abs":"https://arxiv.org/abs/2203.16533v2","url_pdf":"https://arxiv.org/pdf/2203.16533v2.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":"large-scale-pre-training-for-person-re","repo_url":"https://github.com/dengpanfu/luperson-nl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"large-scale-pre-training-for-person-re","repo_url":"https://github.com/DengpanFu/LUPerson","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"multi-object-tracking","task_name":"Multi-Object Tracking"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"online-multi-object-tracking","task_name":"Online Multi-Object Tracking"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"unsupervised-pre-training","task_name":"Unsupervised Pre-training"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/person-re-identification-on-cuhk03","task":"Person Re-Identification","dataset":"CUHK03","model":"Weakly Supervised Pre-training (ResNet50+BDB)","rank_in_archive_order":8,"of":19,"metrics":{"MAP":"82.3","Rank-1":"84.7"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-dukemtmc-reid","task":"Person Re-Identification","dataset":"DukeMTMC-reID","model":"Weakly Supervised Pre-training (ResNet50+MGN)","rank_in_archive_order":23,"of":94,"metrics":{"Rank-1":"92.0","mAP":"84.3"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-msmt17","task":"Person Re-Identification","dataset":"MSMT17","model":"Weakly Supervised Pre-training (ResNet50+MGN)","rank_in_archive_order":16,"of":43,"metrics":{"Rank-1":"86.0","mAP":"68.0"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-market-1501","task":"Person Re-Identification","dataset":"Market-1501","model":"Weakly Supervised Pre-training (ResNet50+MGN)","rank_in_archive_order":13,"of":135,"metrics":{"Rank-1":"96.6","mAP":"91.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.16533","atlas_url":"https://app.syntology.ai/?focus=2203.16533","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16533"}},"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/dengpanfu/luperson-nl","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/ifzhang/FairMOT","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DengpanFu/LUPerson","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/DengpanFu/LUPerson-NL","reach":{"status":"ok"}}],"summary":{"ran":3,"ran_fixture":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"listed":{"samples":2,"ran":2,"repositories":1},"found_in_text":{"samples":1,"ran":1,"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":4,"samples":[{"code_sha256_prefix":"824bbbae4296cf5d","entry":"PNL","repo":"DengpanFu/LUPerson-NL","repo_kind":"official","path":"PNL/libs/pnl_builder.py","file_url":"https://github.com/DengpanFu/LUPerson-NL/blob/HEAD/PNL/libs/pnl_builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"824bbbae4296cf5d"}},{"code_sha256_prefix":"e853d56ab2fb4cee","entry":"SupConLoss","repo":"DengpanFu/LUPerson","repo_kind":"listed","path":"lup_moco/libs/losses.py","file_url":"https://github.com/DengpanFu/LUPerson/blob/HEAD/lup_moco/libs/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e853d56ab2fb4cee"}},{"code_sha256_prefix":"8f7aac120b9147a0","entry":"TripletLoss","repo":"ifzhang/FairMOT","repo_kind":"found_in_text","path":"src/lib/models/losses.py","file_url":"https://github.com/ifzhang/FairMOT/blob/HEAD/src/lib/models/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8f7aac120b9147a0"}},{"code_sha256_prefix":"776cf8f7d3afedb2","entry":"logits_accuracy","repo":"DengpanFu/LUPerson-NL","repo_kind":"official","path":"PNL/libs/pnl_builder.py","file_url":"https://github.com/DengpanFu/LUPerson-NL/blob/HEAD/PNL/libs/pnl_builder.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"776cf8f7d3afedb2"}},{"code_sha256_prefix":"fa79bdd65fc85d81","entry":"logits_accuracy","repo":"DengpanFu/LUPerson","repo_kind":"listed","path":"lup_moco/libs/losses.py","file_url":"https://github.com/DengpanFu/LUPerson/blob/HEAD/lup_moco/libs/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fa79bdd65fc85d81"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}