A Simple Approach to Adversarial Robustness in Few-shot Image Classification
This addresses the robustness issue in few-shot learning for AI applications, but it is incremental as it builds on existing adversarial training and centroid methods.
The paper tackles the problem of adversarial vulnerability in few-shot image classification by proposing a simple transfer-learning approach with calibrated centroid-based classification, achieving performance that matches or exceeds state-of-the-art methods on standard benchmarks.
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 calibrated centroid-based classifier in the novel categories, outperforms or is on-par with state-of-the-art advanced 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 is available here: \url{https://github.com/UCDvision/Simple_few_shot.git}