A Simple Approach to Adversarial Robustness in Few-shot Image Classification

Akshayvarun Subramanya, Hamed Pirsiavash

Keywords: Few-shot learning, Robustness, Image Classification

Abstract: Few-shot image classification, where the goal is to generalize to tasks with limited labeled data, has seen great progress over the years. However, the classifiers are vulnerable to adversarial examples, posing a question regarding their generalization capabilities. Recent works have tried to combine meta-learning approaches with adversarial training to improve the robustness of few-shot classifiers. We show that a simple transfer-learning based approach can be used to train adversarially robust few-shot classifiers. We also present a method for novel classification task based on calibrating the centroid of the few-shot category towards the base classes. We show that standard adversarial training on base categories along with centroid-based classifier in the novel categories, outperforms or is on-par with state-of-the-art advanced methods on standard benchmarks such as Mini-ImageNet, CIFAR-FS and CUB datasets. Our method is simple and easy to scale, and with little effort can lead to robust few-shot classifiers.

One-sentence Summary: We present a simple transfer-learning based approach to learn robust few-shot classifiers.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/a-simple-approach-to-adversarial-robustness/code)