{"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/unsupervised-vehicle-re-identification-with","title":"Unsupervised Vehicle Re-identification with Progressive Adaptation","arxiv_id":"2006.11486","date":"2020-06-20","proceeding":null,"authors":["Jinjia Peng","Yang Wang","Huibing Wang","Zhao Zhang","Xianping Fu","Meng Wang"],"abstract":"Vehicle re-identification (reID) aims at identifying vehicles across different non-overlapping cameras views. The existing methods heavily relied on well-labeled datasets for ideal performance, which inevitably causes fateful drop due to the severe domain bias between the training domain and the real-world scenes; worse still, these approaches required full annotations, which is labor-consuming. To tackle these challenges, we propose a novel progressive adaptation learning method for vehicle reID, named PAL, which infers from the abundant data without annotations. For PAL, a data adaptation module is employed for source domain, which generates the images with similar data distribution to unlabeled target domain as ``pseudo target samples''. These pseudo samples are combined with the unlabeled samples that are selected by a dynamic sampling strategy to make training faster. We further proposed a weighted label smoothing (WLS) loss, which considers the similarity between samples with different clusters to balance the confidence of pseudo labels. Comprehensive experimental results validate the advantages of PAL on both VehicleID and VeRi-776 dataset.","url_abs":"https://arxiv.org/abs/2006.11486v1","url_pdf":"https://arxiv.org/pdf/2006.11486v1.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":"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":"label-smoothing","method_name":"Label Smoothing"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-domain-adaptation-on-vehicleid","task":"Unsupervised Domain Adaptation","dataset":"VehicleID to VeRi-776","model":"PAL","rank_in_archive_order":6,"of":14,"metrics":{"Rank-1":"68.17","Rank-10":"-","Rank-5":"79.91","mAP":"42.04"},"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":"PAL","rank_in_archive_order":7,"of":13,"metrics":{"R-1":"41.08","R-10":"-","R-5":"59.12","mAP":"45.14"},"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":"PAL","rank_in_archive_order":8,"of":13,"metrics":{"R-1":"44.25","R-10":"-","R-5":"60.95","mAP":"48.05"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-veri-776-to","task":"Unsupervised Domain Adaptation","dataset":"Veri-776 to VehicleID Small","model":"PAL","rank_in_archive_order":5,"of":8,"metrics":{" mAP":"53.50","R-1":"50.25","R-10":"-","R-5":"64.91"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.11486","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}