Enlarging Discriminative Power by Adding an Extra Class in Unsupervised Domain Adaptation

TL;DR

This paper introduces a novel approach to unsupervised domain adaptation by adding an artificial class with GAN-generated samples, which enhances feature discriminativeness and improves state-of-the-art performance across multiple methods.

Contribution

The paper proposes a generic method of adding an extra artificial class with GAN samples to improve feature discriminativeness in unsupervised domain adaptation.

Findings

Achieves state-of-the-art results on standard benchmarks

Compatible with multiple existing domain adaptation methods

Enhances discriminative power of features in target domain

Abstract

In this paper, we study the problem of unsupervised domain adaptation that aims at obtaining a prediction model for the target domain using labeled data from the source domain and unlabeled data from the target domain. There exists an array of recent research based on the idea of extracting features that are not only invariant for both domains but also provide high discriminative power for the target domain. In this paper, we propose an idea of empowering the discriminativeness: Adding a new, artificial class and training the model on the data together with the GAN-generated samples of the new class. The trained model based on the new class samples is capable of extracting the features that are more discriminative by repositioning data of current classes in the target domain and therefore drawing the decision boundaries more effectively. Our idea is highly generic so that it is compatible with many existing methods such as DANN, VADA, and DIRT-T. We conduct various experiments for the standard data commonly used for the evaluation of unsupervised domain adaptations and demonstrate that our algorithm achieves the SOTA performance for many scenarios.