{"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/prototype-rectification-for-few-shot-learning","title":"Prototype Rectification for Few-Shot Learning","arxiv_id":"1911.10713","date":"2019-11-25","proceeding":"ECCV 2020 8","authors":["Jinlu Liu","Liang Song","Yongqiang Qin"],"abstract":"Few-shot learning requires to recognize novel classes with scarce labeled data. Prototypical network is useful in existing researches, however, training on narrow-size distribution of scarce data usually tends to get biased prototypes. In this paper, we figure out two key influencing factors of the process: the intra-class bias and the cross-class bias. We then propose a simple yet effective approach for prototype rectification in transductive setting. The approach utilizes label propagation to diminish the intra-class bias and feature shifting to diminish the cross-class bias. We also conduct theoretical analysis to derive its rationality as well as the lower bound of the performance. Effectiveness is shown on three few-shot benchmarks. Notably, our approach achieves state-of-the-art performance on both miniImageNet (70.31% on 1-shot and 81.89% on 5-shot) and tieredImageNet (78.74% on 1-shot and 86.92% on 5-shot).","url_abs":"https://arxiv.org/abs/1911.10713v4","url_pdf":"https://arxiv.org/pdf/1911.10713v4.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":"prototype-rectification-for-few-shot-learning","repo_url":"https://github.com/sicara/easy-few-shot-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-dirichlet-4","task":"Few-Shot Image Classification","dataset":"Dirichlet CUB-200 (5-way, 1-shot)","model":"BDCSPN","rank_in_archive_order":3,"of":8,"metrics":{"1:1 Accuracy":"74.5"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-dirichlet-5","task":"Few-Shot Image Classification","dataset":"Dirichlet CUB-200 (5-way, 5-shot)","model":"BDCSPN","rank_in_archive_order":6,"of":8,"metrics":{"1:1 Accuracy":"87.1"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-dirichlet","task":"Few-Shot Image Classification","dataset":"Dirichlet Mini-Imagenet (5-way, 1-shot)","model":"BD-CSPN","rank_in_archive_order":3,"of":12,"metrics":{"1:1 Accuracy":"67.0"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-dirichlet-1","task":"Few-Shot Image Classification","dataset":"Dirichlet Mini-Imagenet (5-way, 5-shot)","model":"BDCSPN","rank_in_archive_order":4,"of":12,"metrics":{"1:1 Accuracy":"80.2"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-dirichlet-2","task":"Few-Shot Image Classification","dataset":"Dirichlet Tiered-Imagenet (5-way, 1-shot)","model":"BDCSPN","rank_in_archive_order":4,"of":9,"metrics":{"1:1 Accuracy":"74.1"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-dirichlet-3","task":"Few-Shot Image Classification","dataset":"Dirichlet Tiered-Imagenet (5-way, 5-shot)","model":"BDCSPN","rank_in_archive_order":5,"of":9,"metrics":{"1:1 Accuracy":"84.8"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-1","task":"Few-Shot Image Classification","dataset":"Mini-ImageNet - 1-Shot Learning","model":"BD-CSPN","rank_in_archive_order":7,"of":16,"metrics":{"Accuracy":"70.31%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.10713","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}