{"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/person-re-identification-with-bias-controlled","title":"Person Re-identification with Bias-controlled Adversarial Training","arxiv_id":"1904.00244","date":"2019-03-30","proceeding":null,"authors":["Sara Iodice","Krystian Mikolajczyk"],"abstract":"Inspired by the effectiveness of adversarial training in the area of\nGenerative Adversarial Networks we present a new approach for learning feature\nrepresentations in person re-identification. We investigate different types of\nbias that typically occur in re-ID scenarios, i.e., pose, body part and camera\nview, and propose a general approach to address them. We introduce an\nadversarial strategy for controlling bias, named Bias-controlled Adversarial\nframework (BCA), with two complementary branches to reduce or to enhance\nbias-related features. The results and comparison to the state of the art on\ndifferent benchmarks show that our framework is an effective strategy for\nperson re-identification. The performance improvements are in both full and\npartial views of persons.","url_abs":"http://arxiv.org/abs/1904.00244v1","url_pdf":"http://arxiv.org/pdf/1904.00244v1.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":"person-re-identification","task_name":"Person Re-Identification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/person-re-identification-on-dukemtmc-reid","task":"Person Re-Identification","dataset":"DukeMTMC-reID","model":"Bias-controlled Adversarial Training","rank_in_archive_order":58,"of":94,"metrics":{"Rank-1":"85.2","mAP":"74.8"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-market-1501","task":"Person Re-Identification","dataset":"Market-1501","model":"Bias-controlled Adversarial Training","rank_in_archive_order":87,"of":135,"metrics":{"Rank-1":"93.1","mAP":"89.3"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}