{"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/benchmarks-for-corruption-invariant-person-re","title":"Benchmarks for Corruption Invariant Person Re-identification","arxiv_id":"2111.00880","date":"2021-11-01","proceeding":null,"authors":["Minghui Chen","Zhiqiang Wang","Feng Zheng"],"abstract":"When deploying person re-identification (ReID) model in safety-critical applications, it is pivotal to understanding the robustness of the model against a diverse array of image corruptions. However, current evaluations of person ReID only consider the performance on clean datasets and ignore images in various corrupted scenarios. In this work, we comprehensively establish six ReID benchmarks for learning corruption invariant representation. In the field of ReID, we are the first to conduct an exhaustive study on corruption invariant learning in single- and cross-modality datasets, including Market-1501, CUHK03, MSMT17, RegDB, SYSU-MM01. After reproducing and examining the robustness performance of 21 recent ReID methods, we have some observations: 1) transformer-based models are more robust towards corrupted images, compared with CNN-based models, 2) increasing the probability of random erasing (a commonly used augmentation method) hurts model corruption robustness, 3) cross-dataset generalization improves with corruption robustness increases. By analyzing the above observations, we propose a strong baseline on both single- and cross-modality ReID datasets which achieves improved robustness against diverse corruptions. Our codes are available on https://github.com/MinghuiChen43/CIL-ReID.","url_abs":"https://arxiv.org/abs/2111.00880v2","url_pdf":"https://arxiv.org/pdf/2111.00880v2.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":"benchmarks-for-corruption-invariant-person-re","repo_url":"https://github.com/MinghuiChen43/CIL-ReID","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cross-view-person-re-identification","task_name":"Cross-Modal Person Re-Identification"},{"task_slug":"generalizable-person-re-identification","task_name":"Generalizable Person Re-identification"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"}],"methods":[{"method_slug":"augmix","method_name":"AugMix"},{"method_slug":"random-erasing","method_name":"Random Erasing"}],"datasets_introduced":[{"slug":"cuhk03-c","name":"CUHK03-C","full_name":"CUHK03-C"},{"slug":"msmt17-c","name":"MSMT17-C","full_name":"MSMT17-C"},{"slug":"market-1501-c","name":"Market-1501-C","full_name":"Market-1501-C"},{"slug":"regdb-c","name":"RegDB-C","full_name":"RegDB-C"},{"slug":"sysu-mm01-c","name":"SYSU-MM01-C","full_name":"SYSU-MM01-C"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/person-re-identification-on-cuhk03-c","task":"Person Re-Identification","dataset":"CUHK03-C","model":"CIL (ResNet-50)","rank_in_archive_order":8,"of":8,"metrics":{"Rank-1":"22.96","mAP":"16.33","mINP":"22.96"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-msmt17-c","task":"Person Re-Identification","dataset":"MSMT17-C","model":"CIL (ResNet-50)","rank_in_archive_order":5,"of":5,"metrics":{"Rank-1":"39.79","mAP":"15.33","mINP":"0.32"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-market-1501-c","task":"Person Re-Identification","dataset":"Market-1501-C","model":"CIL (ResNet-50)","rank_in_archive_order":21,"of":22,"metrics":{"Rank-1":"55.57","mAP":"28.03","mINP":"1.76"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-sysu-mm01-c","task":"Person Re-Identification","dataset":"SYSU-MM01-C","model":"CIL (ResNet-50)","rank_in_archive_order":2,"of":2,"metrics":{"Rank-1 (All Search)":"36.95","Rank-1 (Indoor Search)":"40.73","mAP (All Search)":"35.92","mAP (Indoor Search)":"48.65","mINP (All Search)":"22.48","mINP (Indoor Search)":"43.11"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.00880","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.00880"}},"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":"deterministic:regex_extraction","url":"https://github.com/MinghuiChen43/CIL-ReID","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"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":"a9297ce0fe9cac98","entry":"train_collate_fn","repo":"MinghuiChen43/CIL-ReID","repo_kind":"official","path":"datasets/make_dataloader.py","file_url":"https://github.com/MinghuiChen43/CIL-ReID/blob/HEAD/datasets/make_dataloader.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a9297ce0fe9cac98"}},{"code_sha256_prefix":"c4ae4a3fc4c4703e","entry":"val_collate_fn","repo":"MinghuiChen43/CIL-ReID","repo_kind":"official","path":"datasets/make_dataloader.py","file_url":"https://github.com/MinghuiChen43/CIL-ReID/blob/HEAD/datasets/make_dataloader.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c4ae4a3fc4c4703e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}