{"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-pseudo-labels-interactive-self-training","title":"Dual Pseudo-Labels Interactive Self-Training for Semi-Supervised Visible-Infrared Person Re-Identification","arxiv_id":null,"date":"2023-01-01","proceeding":"ICCV 2023 1","authors":["Jiangming Shi","Yachao Zhang","Xiangbo Yin","Yuan Xie","Zhizhong Zhang","Jianping Fan","Zhongchao shi","Yanyun Qu"],"abstract":"    Visible-infrared person re-identification (VI-ReID) aims to match a specific person from a gallery of images captured from non-overlapping visible and infrared cameras. Most works focus on fully supervised VI-ReID, which requires substantial cross-modality annotation that is more expensive than the annotation in single-modality. To reduce the extensive cost of annotation, we explore two practical semi-supervised settings: uni-semi-supervised (annotating only visible images) and bi-semi-supervised (annotating partially in both modalities). These two semi-supervised settings face two challenges due to the large cross-modality discrepancies and the lack of correspondence supervision between visible and infrared images. Thus, it is difficult to generate reliable pseudo-labels and learn modality-invariant features from noise pseudo-labels. In this paper, we propose a dual pseudo-label interactive self-training (DPIS) for these two semi-supervised VI-ReID. Our DPIS integrates two pseudo-labels generated by distinct models into a hybrid pseudo-label for unlabeled data. However, the hybrid pseudo-label still inevitably contains noise. To eliminate the negative effect of noise pseudo-labels, we introduce three modules: noise label penalty (NLP), noise correspondence calibration (NCC), and unreliable anchor learning (UAL). Specifically, NLP penalizes noise labels, NCC calibrates noisy correspondences, and UAL mines the hard-to-discriminate features. Extensive experimental results on SYSU-MM01 and RegDB demonstrate that our DPIS achieves impressive performance under these two semi-supervised settings.    ","url_abs":"http://openaccess.thecvf.com//content/ICCV2023/html/Shi_Dual_Pseudo-Labels_Interactive_Self-Training_for_Semi-Supervised_Visible-Infrared_Person_Re-Identification_ICCV_2023_paper.html","url_pdf":"http://openaccess.thecvf.com//content/ICCV2023/papers/Shi_Dual_Pseudo-Labels_Interactive_Self-Training_for_Semi-Supervised_Visible-Infrared_Person_Re-Identification_ICCV_2023_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":"dual-pseudo-labels-interactive-self-training","repo_url":"https://github.com/shijiangming1/DPIS","is_official":1,"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":"pseudo-label","task_name":"Pseudo Label"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}