On the Transferability and Discriminability of Repersentation Learning in Unsupervised Domain Adaptation

TL;DR

This paper reveals that effective unsupervised domain adaptation requires both transferability and discriminability of features, proposing a new framework that explicitly enforces these properties to improve performance across diverse datasets.

Contribution

It introduces a novel adversarial UDA framework combining domain alignment with discriminability constraints, supported by an information-theoretic analysis and a new loss function.

Findings

RLGLC outperforms existing methods on benchmark datasets

Theoretical analysis confirms the importance of discriminability in UDA

Proposed method effectively handles class imbalance and semantic variations

Abstract

In this paper, we addressed the limitation of relying solely on distribution alignment and source-domain empirical risk minimization in Unsupervised Domain Adaptation (UDA). Our information-theoretic analysis showed that this standard adversarial-based framework neglects the discriminability of target-domain features, leading to suboptimal performance. To bridge this theoretical-practical gap, we defined "good representation learning" as guaranteeing both transferability and discriminability, and proved that an additional loss term targeting target-domain discriminability is necessary. Building on these insights, we proposed a novel adversarial-based UDA framework that explicitly integrates a domain alignment objective with a discriminability-enhancing constraint. Instantiated as Domain-Invariant Representation Learning with Global and Local Consistency (RLGLC), our method leverages Asymmetrically-Relaxed Wasserstein of Wasserstein Distance (AR-WWD) to address class imbalance and semantic dimension weighting, and employs a local consistency mechanism to preserve fine-grained target-domain discriminative information. Extensive experiments across multiple benchmark datasets demonstrate that RLGLC consistently surpasses state-of-the-art methods, confirming the value of our theoretical perspective and underscoring the necessity of enforcing both transferability and discriminability in adversarial-based UDA.