{
  "id": "2211.01598",
  "version": "v1",
  "published": "2022-11-03T05:58:26.000Z",
  "updated": "2022-11-03T05:58:26.000Z",
  "title": "Robust Few-shot Learning Without Using any Adversarial Samples",
  "authors": [
    "Gaurav Kumar Nayak",
    "Ruchit Rawal",
    "Inder Khatri",
    "Anirban Chakraborty"
  ],
  "comment": "TNNLS Submission (Under Review)",
  "categories": [
    "cs.CV",
    "cs.LG"
  ],
  "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.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-11-03T05:58:26.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "adversarial samples",
      "robust few-shot learning",
      "low-frequency query set features",
      "state-of-the-art adversarial meta-learning methods",
      "base class data"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}