{"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/revisiting-multi-granularity-representation","title":"Revisiting Multi-Granularity Representation via Group Contrastive Learning for Unsupervised Vehicle Re-identification","arxiv_id":"2410.21667","date":"2024-10-29","proceeding":null,"authors":["Zhigang Chang","Shibao Zheng"],"abstract":"Vehicle re-identification (Vehicle ReID) aims at retrieving vehicle images across disjoint surveillance camera views. The majority of vehicle ReID research is heavily reliant upon supervisory labels from specific human-collected datasets for training. When applied to the large-scale real-world scenario, these models will experience dreadful performance declines due to the notable domain discrepancy between the source dataset and the target. To address this challenge, in this paper, we propose an unsupervised vehicle ReID framework (MGR-GCL). It integrates a multi-granularity CNN representation for learning discriminative transferable features and a contrastive learning module responsible for efficient domain adaptation in the unlabeled target domain. Specifically, after training the proposed Multi-Granularity Representation (MGR) on the labeled source dataset, we propose a group contrastive learning module (GCL) to generate pseudo labels for the target dataset, facilitating the domain adaptation process. We conducted extensive experiments and the results demonstrated our superiority against existing state-of-the-art methods.","url_abs":"https://arxiv.org/abs/2410.21667v1","url_pdf":"https://arxiv.org/pdf/2410.21667v1.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":[],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"},{"task_slug":"unsupervised-vehicle-re-identification","task_name":"Unsupervised Vehicle Re-Identification"},{"task_slug":"vehicle-re-identification","task_name":"Vehicle Re-Identification"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-domain-adaptation-on-vehicleid","task":"Unsupervised Domain Adaptation","dataset":"VehicleID to VeRi-776","model":"MGR-GCL","rank_in_archive_order":3,"of":14,"metrics":{"Rank-1":"79.29","Rank-10":"-","Rank-5":"87.95","mAP":"48.73"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-veri-776-to-2","task":"Unsupervised Domain Adaptation","dataset":"Veri-776 to VehicleID Large","model":"MGR-GCL","rank_in_archive_order":5,"of":13,"metrics":{"R-1":"42.83","R-10":"-","R-5":"64.36","mAP":"47.59"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-veri-776-to-1","task":"Unsupervised Domain Adaptation","dataset":"Veri-776 to VehicleID Medium","model":"MGR-GCL","rank_in_archive_order":5,"of":13,"metrics":{"R-1":"45.88","R-10":"-","R-5":"67.65","mAP":"50.56"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}