Adversarial Feature Augmentation for Unsupervised Domain Adaptation
This work addresses the problem of training classifiers for unlabeled target domains using labeled source data, with incremental improvements over existing GAN-based approaches.
The paper tackles unsupervised domain adaptation by extending GAN-based methods to enforce domain-invariance and introduce feature augmentation, achieving superior or comparable performance to state-of-the-art results on several benchmarks.
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.