Rethinking Domain Generalization: Discriminability and Generalizability

TL;DR

This paper introduces DMDA, a novel framework for domain generalization that enhances feature discriminability and robustness by selective pruning and micro-level distribution alignment, outperforming existing methods on benchmark datasets.

Contribution

Proposes DMDA, combining SCP and MDA to improve discriminability and generalizability in domain generalization, addressing limitations of prior invariant feature learning methods.

Findings

DMDA achieves comparable or superior performance on four benchmark datasets.

Selective Channel Pruning enhances feature discriminability by reducing redundancy.

Micro-level Distribution Alignment improves intra-class consistency beyond category-level alignment.

Abstract

Domain generalization(DG) endeavors to develop robust models that possess strong generalizability while preserving excellent discriminability. Nonetheless, pivotal DG techniques tend to improve the feature generalizability by learning domain-invariant representations, inadvertently overlooking the feature discriminability. On the one hand, the simultaneous attainment of generalizability and discriminability of features presents a complex challenge, often entailing inherent contradictions. This challenge becomes particularly pronounced when domain-invariant features manifest reduced discriminability owing to the inclusion of unstable factors, i.e., spurious correlations. On the other hand, prevailing domain-invariant methods can be categorized as category-level alignment, susceptible to discarding indispensable features possessing substantial generalizability and narrowing intra-class variations. To surmount these obstacles, we rethink DG from a new perspective that concurrently imbues features with formidable discriminability and robust generalizability, and present a novel framework, namely, Discriminative Microscopic Distribution Alignment~(DMDA). DMDA incorporates two core components: Selective Channel Pruning~(SCP) and Micro-level Distribution Alignment~(MDA). Concretely, SCP attempts to curtail redundancy within neural networks, prioritizing stable attributes conducive to accurate classification. This approach alleviates the adverse effect of spurious domain invariance and amplifies the feature discriminability. Besides, MDA accentuates micro-level alignment within each class, going beyond mere category-level alignment. Extensive experiments on four benchmark datasets corroborate that DMDA achieves comparable results to state-of-the-art methods in DG, underscoring the efficacy of our method.