{"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/cm-nas-rethinking-cross-modality-neural","title":"CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification","arxiv_id":"2101.08467","date":"2021-01-21","proceeding":"ICCV 2021 10","authors":["Chaoyou Fu","Yibo Hu","Xiang Wu","Hailin Shi","Tao Mei","Ran He"],"abstract":"Visible-Infrared person re-identification (VI-ReID) aims to match cross-modality pedestrian images, breaking through the limitation of single-modality person ReID in dark environment. In order to mitigate the impact of large modality discrepancy, existing works manually design various two-stream architectures to separately learn modality-specific and modality-sharable representations. Such a manual design routine, however, highly depends on massive experiments and empirical practice, which is time consuming and labor intensive. In this paper, we systematically study the manually designed architectures, and identify that appropriately separating Batch Normalization (BN) layers is the key to bring a great boost towards cross-modality matching. Based on this observation, the essential objective is to find the optimal separation scheme for each BN layer. To this end, we propose a novel method, named Cross-Modality Neural Architecture Search (CM-NAS). It consists of a BN-oriented search space in which the standard optimization can be fulfilled subject to the cross-modality task. Equipped with the searched architecture, our method outperforms state-of-the-art counterparts in both two benchmarks, improving the Rank-1/mAP by 6.70%/6.13% on SYSU-MM01 and by 12.17%/11.23% on RegDB. Code is released at https://github.com/JDAI-CV/CM-NAS.","url_abs":"https://arxiv.org/abs/2101.08467v3","url_pdf":"https://arxiv.org/pdf/2101.08467v3.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":"cm-nas-rethinking-cross-modality-neural","repo_url":"https://github.com/jdai-cv/cm-nas","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2101.08467","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.08467"}},"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/jdai-cv/cm-nas","reach":null}],"summary":{"ran":3,"unverified":5},"by_repo_kind":{"official":{"samples":8,"ran":3,"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":"d0c476f56de6f6ae","entry":"BottleneckSwitchBN","repo":"jdai-cv/cm-nas","repo_kind":"official","path":"models/model_eval_op.py","file_url":"https://github.com/jdai-cv/cm-nas/blob/HEAD/models/model_eval_op.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":"d0c476f56de6f6ae"}},{"code_sha256_prefix":"4c7df05474133fab","entry":"DownsampleSwitchBN","repo":"jdai-cv/cm-nas","repo_kind":"official","path":"models/model_eval_op.py","file_url":"https://github.com/jdai-cv/cm-nas/blob/HEAD/models/model_eval_op.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4c7df05474133fab"}},{"code_sha256_prefix":"b9856d7c4ec9babd","entry":"SwitchBatchNorm2d","repo":"jdai-cv/cm-nas","repo_kind":"official","path":"models/model_eval_op.py","file_url":"https://github.com/jdai-cv/cm-nas/blob/HEAD/models/model_eval_op.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":"b9856d7c4ec9babd"}},{"code_sha256_prefix":"17825e7bad73b9b7","entry":"ResNetUnfoldSwitchBN","repo":"jdai-cv/cm-nas","repo_kind":"official","path":"models/model_eval_op.py","file_url":"https://github.com/jdai-cv/cm-nas/blob/HEAD/models/model_eval_op.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":"17825e7bad73b9b7"}},{"code_sha256_prefix":"b84cdbe3901e586d","entry":"TwoStreamSwitchBNOp","repo":"jdai-cv/cm-nas","repo_kind":"official","path":"models/model_eval_op.py","file_url":"https://github.com/jdai-cv/cm-nas/blob/HEAD/models/model_eval_op.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":"b84cdbe3901e586d"}},{"code_sha256_prefix":"a47ae8259ee2ffa5","entry":"resnet50unfold_switchbn","repo":"jdai-cv/cm-nas","repo_kind":"official","path":"models/model_eval_op.py","file_url":"https://github.com/jdai-cv/cm-nas/blob/HEAD/models/model_eval_op.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":"a47ae8259ee2ffa5"}},{"code_sha256_prefix":"879845a7088a8d3f","entry":"weights_init_classifier","repo":"jdai-cv/cm-nas","repo_kind":"official","path":"models/model_eval_op.py","file_url":"https://github.com/jdai-cv/cm-nas/blob/HEAD/models/model_eval_op.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":"879845a7088a8d3f"}},{"code_sha256_prefix":"7d29cff2640ae7d6","entry":"weights_init_kaiming","repo":"jdai-cv/cm-nas","repo_kind":"official","path":"models/model_eval_op.py","file_url":"https://github.com/jdai-cv/cm-nas/blob/HEAD/models/model_eval_op.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":"7d29cff2640ae7d6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}