{"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/dual-level-viewpoint-learning-for-cross","title":"Dual-Level Viewpoint-Learning for Cross-Domain Vehicle Re-Identification","arxiv_id":null,"date":"2024-05-08","proceeding":"Electronics 2024 5","authors":["Zhou R","Wang Q","Cao L","Xu J","Zhu X","Xiong X","Zhang H","Zhong Y"],"abstract":"The definition of vehicle viewpoint annotations is ambiguous due to human subjective judgment, which makes the cross-domain vehicle re-identification methods unable to learn the viewpoint invariance features during source domain pre-training. This will further lead to cross-view misalignment in downstream target domain tasks. To solve the above challenges, this paper presents a dual-level viewpoint-learning framework that contains an angle invariance pre-training method and a meta-orientation adaptation learning strategy. The dual-level viewpoint-annotation proposal is first designed to concretely redefine the vehicle viewpoint from two aspects (i.e., angle-level and orientation-level). An angle invariance pre-training method is then proposed to preserve identity similarity and difference across the cross-view; this consists of a part-level pyramidal network and an angle bias metric loss. Under the supervision of angle bias metric loss, the part-level pyramidal network, as the backbone, learns the subtle differences of vehicles from different angle-level viewpoints. Finally, a meta-orientation adaptation learning strategy is designed to extend the generalization ability of the re-identification model to the unseen orientation-level viewpoints. Simultaneously, the proposed meta-learning strategy enforces meta-orientation training and meta-orientation testing according to the orientation-level viewpoints in the target domain. Extensive experiments on public vehicle re-identification datasets demonstrate that the proposed method combines the redefined dual-level viewpoint-information and significantly outperforms other state-of-the-art methods in alleviating viewpoint variations.","url_abs":"https://www.mdpi.com/2079-9292/13/10/1823","url_pdf":"https://www.mdpi.com/2079-9292/13/10/1823/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":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"},{"task_slug":"vehicle-re-identification","task_name":"Vehicle Re-Identification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-domain-adaptation-on-vehicleid-3","task":"Unsupervised Domain Adaptation","dataset":"VehicleID to VERI-Wild Large","model":"DLVL","rank_in_archive_order":3,"of":9,"metrics":{"R-1":"41.8","R-10":"-","R-5":"65.8","mAP":"21.7"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-vehicleid-2","task":"Unsupervised Domain Adaptation","dataset":"VehicleID to VERI-Wild Medium","model":"DLVL","rank_in_archive_order":3,"of":9,"metrics":{"R-1":"51.9","R-10":"-","R-5":"74.9","mAP":"27.3"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-vehicleid-1","task":"Unsupervised Domain Adaptation","dataset":"VehicleID to VERI-Wild Small","model":"DLVL","rank_in_archive_order":3,"of":9,"metrics":{"R-1":"59.9","R-10":"-","R-5":"80.7","mAP":"31.4"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}