{"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/msinet-twins-contrastive-search-of-multi","title":"MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID","arxiv_id":"2303.07065","date":"2023-03-13","proceeding":"CVPR 2023 1","authors":["Jianyang Gu","Kai Wang","Hao Luo","Chen Chen","Wei Jiang","Yuqiang Fang","Shanghang Zhang","Yang You","Jian Zhao"],"abstract":"Neural Architecture Search (NAS) has been increasingly appealing to the society of object Re-Identification (ReID), for that task-specific architectures significantly improve the retrieval performance. Previous works explore new optimizing targets and search spaces for NAS ReID, yet they neglect the difference of training schemes between image classification and ReID. In this work, we propose a novel Twins Contrastive Mechanism (TCM) to provide more appropriate supervision for ReID architecture search. TCM reduces the category overlaps between the training and validation data, and assists NAS in simulating real-world ReID training schemes. We then design a Multi-Scale Interaction (MSI) search space to search for rational interaction operations between multi-scale features. In addition, we introduce a Spatial Alignment Module (SAM) to further enhance the attention consistency confronted with images from different sources. Under the proposed NAS scheme, a specific architecture is automatically searched, named as MSINet. Extensive experiments demonstrate that our method surpasses state-of-the-art ReID methods on both in-domain and cross-domain scenarios. Source code available in https://github.com/vimar-gu/MSINet.","url_abs":"https://arxiv.org/abs/2303.07065v1","url_pdf":"https://arxiv.org/pdf/2303.07065v1.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":"msinet-twins-contrastive-search-of-multi","repo_url":"https://github.com/vimar-gu/msinet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"vehicle-re-identification","task_name":"Vehicle Re-Identification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/person-re-identification-on-msmt17","task":"Person Re-Identification","dataset":"MSMT17","model":"MSINet (2.3M w/o RK)","rank_in_archive_order":32,"of":43,"metrics":{"Rank-1":"81","mAP":"59.6"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-market-1501","task":"Person Re-Identification","dataset":"Market-1501","model":"MSINet (2.3M w/o RK)","rank_in_archive_order":63,"of":135,"metrics":{"Rank-1":"95.3","mAP":"89.6"},"uses_additional_data":false},{"leaderboard":"/sota/vehicle-re-identification-on-veri-776","task":"Vehicle Re-Identification","dataset":"VeRi-776","model":"MSINet (2.3M w/o RK)","rank_in_archive_order":14,"of":17,"metrics":{"Rank-1":"96.8","mAP":"78.8"},"uses_additional_data":false},{"leaderboard":"/sota/vehicle-re-identification-on-vehicleid-large","task":"Vehicle Re-Identification","dataset":"VehicleID Large","model":"MSINet (2.3M w/o RK)","rank_in_archive_order":8,"of":10,"metrics":{"Rank-1":"77.9","Rank-5":"91.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.07065","atlas_url":"https://app.syntology.ai/?focus=2303.07065","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}