{"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/make-svm-great-again-with-siamese-kernel-for","title":"Make SVM great again with Siamese kernel for few-shot learning","arxiv_id":null,"date":"2018-01-01","proceeding":"ICLR 2018 1","authors":["Bence Tilk"],"abstract":"While deep neural networks have shown outstanding results in a wide range of applications,\nlearning from a very limited number of examples is still a challenging\ntask. Despite the difficulties of the few-shot learning, metric-learning techniques\nshowed the potential of the neural networks for this task. While these methods\nperform well, they don’t provide satisfactory results. In this work, the idea of\nmetric-learning is extended with Support Vector Machines (SVM) working mechanism,\nwhich is well known for generalization capabilities on a small dataset.\nFurthermore, this paper presents an end-to-end learning framework for training\nadaptive kernel SVMs, which eliminates the problem of choosing a correct kernel\nand good features for SVMs. Next, the one-shot learning problem is redefined\nfor audio signals. Then the model was tested on vision task (using Omniglot\ndataset) and speech task (using TIMIT dataset) as well. Actually, the algorithm\nusing Omniglot dataset improved accuracy from 98.1% to 98.5% on the one-shot\nclassification task and from 98.9% to 99.3% on the few-shot classification task.","url_abs":"https://openreview.net/forum?id=B1EVwkqTW","url_pdf":"https://openreview.net/pdf?id=B1EVwkqTW","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":"make-svm-great-again-with-siamese-kernel-for","repo_url":"https://github.com/tilkb/siamese-kernel-machine","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"one-shot-learning","task_name":"One-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}