{"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/laplacian-regularized-few-shot-learning","title":"Laplacian Regularized Few-Shot Learning","arxiv_id":null,"date":"2020-06-29","proceeding":"ICML 2020 1","authors":["Imtiaz Masud Ziko; Jose Dolz; Eric Granger; Ismail Ben Ayed"],"abstract":"We propose a transductive Laplacian-regularized inference for few-shot tasks. Given any feature embedding learned from the base classes, we minimize a quadratic binary-assignment function containing two terms: (1) a unary term assign- ing query samples to the nearest class prototype, and (2) a pairwise Laplacian term encouraging nearby query samples to have consistent label as- signments. Our transductive inference does not re-train the base model, and can be viewed as a graph clustering of the query set, subject to super- vision constraints from the support set. We derive a computationally efficient bound optimizer of a relaxation of our function, which computes inde- pendent (parallel) updates for each query sample, while guaranteeing convergence. Following a sim- ple cross-entropy training on the base classes, and without complex meta-learning strategies, we con- ducted comprehensive experiments over five few- shot learning benchmarks. Our LaplacianShot consistently outperforms state-of-the-art methods by significant margins across different models, settings, and data sets. Furthermore, our trans- ductive inference is very fast, with computational times that are close to inductive inference, and can be used for large-scale few-shot tasks.","url_abs":"https://arxiv.org/abs/2006.15486","url_pdf":"https://arxiv.org/pdf/2006.15486.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":"laplacian-regularized-few-shot-learning","repo_url":"https://github.com/imtiazziko/LaplacianShot","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"laplacian-regularized-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":"clustering","task_name":"Clustering"},{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"graph-clustering","task_name":"Graph Clustering"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[{"method_slug":"transductive-inference","method_name":"Transductive Inference"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-5-1","task":"Few-Shot Image Classification","dataset":"CUB 200 5-way 1-shot","model":"LaplacianShot","rank_in_archive_order":18,"of":36,"metrics":{"Accuracy":"80.96"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-5","task":"Few-Shot Image Classification","dataset":"CUB 200 5-way 5-shot","model":"LaplacianShot","rank_in_archive_order":22,"of":32,"metrics":{"Accuracy":"88.68"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-6","task":"Few-Shot Image Classification","dataset":"Mini-ImageNet-CUB 5-way (5-shot)","model":"LaplacianShot","rank_in_archive_order":5,"of":8,"metrics":{"Accuracy":"66.33"},"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":"LaplacianShot","rank_in_archive_order":23,"of":105,"metrics":{"Accuracy":"75.57"},"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":"LaplacianShot","rank_in_archive_order":25,"of":95,"metrics":{"Accuracy":"84.72"},"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":"LaplacianShot","rank_in_archive_order":11,"of":49,"metrics":{"Accuracy":"80.30"},"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":"LaplacianShot","rank_in_archive_order":16,"of":51,"metrics":{"Accuracy":"87.93"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-inaturalist","task":"Few-Shot Image Classification","dataset":"iNaturalist (227-way multi-shot)","model":"LaplacianShot","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"74.97"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-miniimagenet-1","task":"Few-Shot Image Classification","dataset":"miniImagenet → CUB (5-way 1-shot)","model":"LaplacianShot","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"55.46"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-miniimagenet-2","task":"Few-Shot Image Classification","dataset":"miniImagenet → CUB (5-way 5-shot)","model":"LaplacianShot","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"66.33"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}