{"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/robust-few-shot-learning-without-using-any","title":"Robust Few-shot Learning Without Using any Adversarial Samples","arxiv_id":"2211.01598","date":"2022-11-03","proceeding":null,"authors":["Gaurav Kumar Nayak","Ruchit Rawal","Inder Khatri","Anirban Chakraborty"],"abstract":"The high cost of acquiring and annotating samples has made the `few-shot' learning problem of prime importance. Existing works mainly focus on improving performance on clean data and overlook robustness concerns on the data perturbed with adversarial noise. Recently, a few efforts have been made to combine the few-shot problem with the robustness objective using sophisticated Meta-Learning techniques. These methods rely on the generation of adversarial samples in every episode of training, which further adds a computational burden. To avoid such time-consuming and complicated procedures, we propose a simple but effective alternative that does not require any adversarial samples. Inspired by the cognitive decision-making process in humans, we enforce high-level feature matching between the base class data and their corresponding low-frequency samples in the pretraining stage via self distillation. The model is then fine-tuned on the samples of novel classes where we additionally improve the discriminability of low-frequency query set features via cosine similarity. On a 1-shot setting of the CIFAR-FS dataset, our method yields a massive improvement of $60.55\\%$ & $62.05\\%$ in adversarial accuracy on the PGD and state-of-the-art Auto Attack, respectively, with a minor drop in clean accuracy compared to the baseline. Moreover, our method only takes $1.69\\times$ of the standard training time while being $\\approx$ $5\\times$ faster than state-of-the-art adversarial meta-learning methods. The code is available at https://github.com/vcl-iisc/robust-few-shot-learning.","url_abs":"https://arxiv.org/abs/2211.01598v1","url_pdf":"https://arxiv.org/pdf/2211.01598v1.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":"robust-few-shot-learning-without-using-any","repo_url":"https://github.com/vcl-iisc/robust-few-shot-learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}