Adversarial Feature Augmentation for Cross-domain Few-shot Classification

TL;DR

This paper introduces an adversarial feature augmentation technique to reduce domain gap in cross-domain few-shot classification, improving generalization across diverse datasets.

Contribution

The paper proposes a novel adversarial feature augmentation method that enhances cross-domain few-shot learning by simulating distribution variations through adversarial training.

Findings

Outperforms state-of-the-art methods on nine datasets

Effectively reduces domain discrepancy in few-shot tasks

Easily integrates with existing meta-learning frameworks

Abstract

Existing methods based on meta-learning predict novel-class labels for (target domain) testing tasks via meta knowledge learned from (source domain) training tasks of base classes. However, most existing works may fail to generalize to novel classes due to the probably large domain discrepancy across domains. To address this issue, we propose a novel adversarial feature augmentation (AFA) method to bridge the domain gap in few-shot learning. The feature augmentation is designed to simulate distribution variations by maximizing the domain discrepancy. During adversarial training, the domain discriminator is learned by distinguishing the augmented features (unseen domain) from the original ones (seen domain), while the domain discrepancy is minimized to obtain the optimal feature encoder. The proposed method is a plug-and-play module that can be easily integrated into existing few-shot learning methods based on meta-learning. Extensive experiments on nine datasets demonstrate the superiority of our method for cross-domain few-shot classification compared with the state of the art. Code is available at https://github.com/youthhoo/AFA_For_Few_shot_learning