Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment

TL;DR

This paper introduces a Gaussian-guided latent alignment method for unsupervised domain adaptation, improving feature transferability across domains by aligning latent distributions under a prior, leading to better generalization.

Contribution

The paper proposes a novel Gaussian-guided latent alignment approach with an unpaired L1-distance for improved domain feature alignment in unsupervised adaptation.

Findings

Outperforms state-of-the-art methods on nine benchmarks.

Enhances feature alignment across large domain gaps.

Demonstrates versatility and significant improvement over existing techniques.

Abstract

In this study, we focus on the unsupervised domain adaptation problem where an approximate inference model is to be learned from a labeled data domain and expected to generalize well to an unlabeled data domain. The success of unsupervised domain adaptation largely relies on the cross-domain feature alignment. Previous work has attempted to directly align latent features by the classifier-induced discrepancies. Nevertheless, a common feature space cannot always be learned via this direct feature alignment especially when a large domain gap exists. To solve this problem, we introduce a Gaussian-guided latent alignment approach to align the latent feature distributions of the two domains under the guidance of the prior distribution. In such an indirect way, the distributions over the samples from the two domains will be constructed on a common feature space, i.e., the space of the prior, which promotes better feature alignment. To effectively align the target latent distribution with this prior distribution, we also propose a novel unpaired L1-distance by taking advantage of the formulation of the encoder-decoder. The extensive evaluations on nine benchmark datasets validate the superior knowledge transferability through outperforming state-of-the-art methods and the versatility of the proposed method by improving the existing work significantly.