{"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/aggregating-deep-pyramidal-representations","title":"Aggregating Deep Pyramidal Representations for Person Re-Idenfitication","arxiv_id":null,"date":"2019-06-20","proceeding":"International Conference on Computer Vision and Pattern Recognition Workshops (CVPR) 2019 6","authors":["Niki Martinel","Gian Luca Foresti","Christian Micheloni"],"abstract":"Learning discriminative, view-invariant and multi-scale representations of person appearance with different se- mantic levels is of paramount importance for person Re- Identification (Re-ID). A surge of effort has been spent by the community to learn deep Re-ID models capturing a holistic single semantic level feature representation. To improve the achieved results, additional visual attributes and body part-driven models have been considered. How- ever, these require extensive human annotation labor or de- mand additional computational efforts. We argue that a pyramid-inspired method capturing multi-scale information may overcome such requirements. Precisely, multi-scale stripes that represent visual information of a person can be used by a novel architecture factorizing them into latent discriminative factors at multiple semantic levels. A multi- task loss is combined with a curriculum learning strategy to learn a discriminative and invariant person representation which is exploited for triplet-similarity learning. Results on three benchmark Re-ID datasets demonstrate that better performance than existing methods are achieved (e.g., more than 90% accuracy on the Duke-MTMC dataset).","url_abs":"http://openaccess.thecvf.com/content_CVPRW_2019/papers/TRMTMCT/Martinel_Aggregating_Deep_Pyramidal_Representations_for_Person_Re-Identification_CVPRW_2019_paper.pdf","url_pdf":"http://openaccess.thecvf.com/content_CVPRW_2019/papers/TRMTMCT/Martinel_Aggregating_Deep_Pyramidal_Representations_for_Person_Re-Identification_CVPRW_2019_paper.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":"aggregating-deep-pyramidal-representations","repo_url":"https://github.com/iN1k1/deep-pyramidal-representations-person-re-identification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":null,"task_name":"Triplet"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/person-re-identification-on-dukemtmc-reid","task":"Person Re-Identification","dataset":"DukeMTMC-reID","model":"PyrNet (+ReRank)","rank_in_archive_order":18,"of":94,"metrics":{"Rank-1":"90.3","mAP":"87.7"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-dukemtmc-reid","task":"Person Re-Identification","dataset":"DukeMTMC-reID","model":"PyrNet","rank_in_archive_order":60,"of":94,"metrics":{"Rank-1":"87.1","mAP":"74.0"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-market-1501","task":"Person Re-Identification","dataset":"Market-1501","model":"PyrNet (multi-shot+ReRank)","rank_in_archive_order":27,"of":135,"metrics":{"Rank-1":"96.1","mAP":"94.0"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-market-1501","task":"Person Re-Identification","dataset":"Market-1501","model":"PyrNet (multi-shot)","rank_in_archive_order":68,"of":135,"metrics":{"Rank-1":"95.2","mAP":"86.7"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-market-1501","task":"Person Re-Identification","dataset":"Market-1501","model":"PyrNet (single-shot+ReRank)","rank_in_archive_order":77,"of":135,"metrics":{"Rank-1":"94.6","mAP":"91.4"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-market-1501","task":"Person Re-Identification","dataset":"Market-1501","model":"PyrNet (single-shot)","rank_in_archive_order":85,"of":135,"metrics":{"Rank-1":"93.6","mAP":"81.7"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}