Adversarially Robust Few-shot Learning through Simple Transfer

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. Previous 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 calibrated centroid-based classifier in the novel categories, outperforms or is on-par with previous methods on standard benchmarks for few-shot learning. Our method is simple, easy to scale, and with little effort can lead to robust few-shot classifiers. Code: https://github.com/UCDvision/Simple_few_shot.git