{"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/meta-learning-with-differentiable-convex","title":"Meta-Learning with Differentiable Convex Optimization","arxiv_id":"1904.03758","date":"2019-04-07","proceeding":"CVPR 2019 6","authors":["Kwonjoon Lee","Subhransu Maji","Avinash Ravichandran","Stefano Soatto"],"abstract":"Many meta-learning approaches for few-shot learning rely on simple base\nlearners such as nearest-neighbor classifiers. However, even in the few-shot\nregime, discriminatively trained linear predictors can offer better\ngeneralization. We propose to use these predictors as base learners to learn\nrepresentations for few-shot learning and show they offer better tradeoffs\nbetween feature size and performance across a range of few-shot recognition\nbenchmarks. Our objective is to learn feature embeddings that generalize well\nunder a linear classification rule for novel categories. To efficiently solve\nthe objective, we exploit two properties of linear classifiers: implicit\ndifferentiation of the optimality conditions of the convex problem and the dual\nformulation of the optimization problem. This allows us to use high-dimensional\nembeddings with improved generalization at a modest increase in computational\noverhead. Our approach, named MetaOptNet, achieves state-of-the-art performance\non miniImageNet, tieredImageNet, CIFAR-FS, and FC100 few-shot learning\nbenchmarks. Our code is available at https://github.com/kjunelee/MetaOptNet.","url_abs":"http://arxiv.org/abs/1904.03758v2","url_pdf":"http://arxiv.org/pdf/1904.03758v2.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":"meta-learning-with-differentiable-convex","repo_url":"https://github.com/kjunelee/MetaOptNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"meta-learning-with-differentiable-convex","repo_url":"https://github.com/cyvius96/few-shot-meta-baseline","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"meta-learning-with-differentiable-convex","repo_url":"https://github.com/goldblum/AdversarialQuerying","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"meta-learning-with-differentiable-convex","repo_url":"https://github.com/nupurkmr9/S2M2_fewshot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"meta-learning-with-differentiable-convex","repo_url":"https://github.com/xiangyu8/PT-MAP-sf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"meta-learning-with-differentiable-convex","repo_url":"https://github.com/yinboc/few-shot-meta-baseline","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"meta-learning-with-differentiable-convex","repo_url":"https://github.com/learnables/learn2learn","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"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-5","task":"Few-Shot Image Classification","dataset":"CIFAR-FS 5-way (1-shot)","model":"MetaOptNet-SVM-trainval","rank_in_archive_order":32,"of":38,"metrics":{"Accuracy":"72.8"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-5-1","task":"Few-Shot Image Classification","dataset":"CIFAR-FS 5-way (5-shot)","model":"MetaOptNet-SVM-trainval","rank_in_archive_order":32,"of":39,"metrics":{"Accuracy":"85"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-fc100-5-way","task":"Few-Shot Image Classification","dataset":"FC100 5-way (1-shot)","model":"MetaOptNet-SVM-trainval","rank_in_archive_order":12,"of":22,"metrics":{"Accuracy":"47.2"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-fc100-5-way-1","task":"Few-Shot Image Classification","dataset":"FC100 5-way (5-shot)","model":"MetaOptNet-SVM-trainval","rank_in_archive_order":14,"of":22,"metrics":{"Accuracy":"62.5"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-2","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (1-shot)","model":"MetaOptNet-SVM-trainval","rank_in_archive_order":63,"of":105,"metrics":{"Accuracy":"64.09"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-3","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (5-shot)","model":"MetaOptNet-SVM-trainval","rank_in_archive_order":54,"of":95,"metrics":{"Accuracy":"80"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-tiered","task":"Few-Shot Image Classification","dataset":"Tiered ImageNet 5-way (1-shot)","model":"MetaOptNet-SVM-trainval","rank_in_archive_order":43,"of":49,"metrics":{"Accuracy":"65.81"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-tiered-1","task":"Few-Shot Image Classification","dataset":"Tiered ImageNet 5-way (5-shot)","model":"MetaOptNet-SVM-trainval","rank_in_archive_order":42,"of":51,"metrics":{"Accuracy":"81.75"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.03758","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}