Adversarial Feature Augmentation for Unsupervised Domain Adaptation

TL;DR

This paper introduces a novel approach for unsupervised domain adaptation that combines domain-invariant feature learning with feature augmentation via GANs, leading to improved classifier performance across benchmarks.

Contribution

It extends existing GAN-based domain adaptation methods by incorporating feature augmentation and enforcing domain-invariance in the feature extractor.

Findings

Feature augmentation improves adaptation performance.

Enforcing domain-invariance enhances classifier accuracy.

Achieves state-of-the-art or comparable results on benchmarks.

Abstract

Recent works showed that Generative Adversarial Networks (GANs) can be successfully applied in unsupervised domain adaptation, where, given a labeled source dataset and an unlabeled target dataset, the goal is to train powerful classifiers for the target samples. In particular, it was shown that a GAN objective function can be used to learn target features indistinguishable from the source ones. In this work, we extend this framework by (i) forcing the learned feature extractor to be domain-invariant, and (ii) training it through data augmentation in the feature space, namely performing feature augmentation. While data augmentation in the image space is a well established technique in deep learning, feature augmentation has not yet received the same level of attention. We accomplish it by means of a feature generator trained by playing the GAN minimax game against source features. Results show that both enforcing domain-invariance and performing feature augmentation lead to superior or comparable performance to state-of-the-art results in several unsupervised domain adaptation benchmarks.