{"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/long-tailed-multi-label-visual-recognition-by","title":"Long-Tailed Multi-Label Visual Recognition by Collaborative Training on Uniform and Re-Balanced Samplings","arxiv_id":null,"date":"2021-06-19","proceeding":"CVPR 2021 1","authors":["Hao Guo","Song Wang"],"abstract":"    Long-tailed data distribution is common in many multi-label visual recognition tasks and the direct use of these data for training usually leads to relatively low performance on tail classes. While re-balanced data sampling can improve the performance on tail classes, it may also hurt the performance on head classes in training due to label co-occurrence. In this paper, we propose a new approach to train on both uniform and re-balanced samplings in a collaborative way, resulting in performance improvement on both head and tail classes. More specifically, we design a visual recognition network with two branches: one takes the uniform sampling as input while the other takes the re-balanced sampling as the input. For each branch, we conduct visual recognition using a binary-cross-entropy-based classification loss with learnable logit compensation. We further define a new cross-branch loss to enforce the consistency when the same input image goes through the two branches. We conduct extensive experiments on VOC-LT and COCO-LT datasets. The results show that the proposed method significantly outperforms previous state-of-the-art methods on long-tailed multi-label visual recognition.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2021/html/Guo_Long-Tailed_Multi-Label_Visual_Recognition_by_Collaborative_Training_on_Uniform_and_CVPR_2021_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2021/papers/Guo_Long-Tailed_Multi-Label_Visual_Recognition_by_Collaborative_Training_on_Uniform_and_CVPR_2021_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":[],"tasks":[{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/long-tail-learning-on-coco-mlt","task":"Long-tail Learning","dataset":"COCO-MLT","model":"LTML(ResNet-50)","rank_in_archive_order":4,"of":13,"metrics":{"Average mAP":"56.90"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-voc-mlt","task":"Long-tail Learning","dataset":"VOC-MLT","model":"LTML(ResNet-50)","rank_in_archive_order":5,"of":13,"metrics":{"Average mAP":"81.44"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}