Learning a Domain-Invariant Embedding for Unsupervised Domain Adaptation Using Class-Conditioned Distribution Alignment

TL;DR

This paper proposes a method for unsupervised domain adaptation by learning a domain-invariant embedding space using class-conditioned distribution alignment and the Sliced-Wasserstein Distance, achieving state-of-the-art results.

Contribution

It introduces a novel approach combining distribution alignment with class-conditioned pseudo-labeling to improve domain adaptation performance.

Findings

Achieves state-of-the-art results on UDA benchmarks.

Effectively aligns class distributions across domains.

Enhances generalization of classifiers to target domain.

Abstract

We address the problem of unsupervised domain adaptation (UDA) by learning a cross-domain agnostic embedding space, where the distance between the probability distributions of the two source and target visual domains is minimized. We use the output space of a shared cross-domain deep encoder to model the embedding space anduse the Sliced-Wasserstein Distance (SWD) to measure and minimize the distance between the embedded distributions of two source and target domains to enforce the embedding to be domain-agnostic.Additionally, we use the source domain labeled data to train a deep classifier from the embedding space to the label space to enforce the embedding space to be discriminative.As a result of this training scheme, we provide an effective solution to train the deep classification network on the source domain such that it will generalize well on the target domain, where only unlabeled training data is accessible. To mitigate the challenge of class matching, we also align corresponding classes in the embedding space by using high confidence pseudo-labels for the target domain, i.e. assigning the class for which the source classifier has a high prediction probability. We provide experimental results on UDA benchmark tasks to demonstrate that our method is effective and leads to state-of-the-art performance.