Guidance Not Obstruction: A Conjugate Consistent Enhanced Strategy for Domain Generalization

TL;DR

This paper introduces Con2EM, a novel domain generalization strategy that enhances discriminative class separation across domains by leveraging a distribution-level Universum approach, outperforming existing methods.

Contribution

It proposes a new conjugate consistent module, Con2EM, utilizing a meta-distribution and Universum strategy to improve domain generalization by focusing on class discrimination.

Findings

Effective in improving domain generalization performance

Achieves lower computational cost than state-of-the-art methods

Enhances class discrimination across diverse domains

Abstract

Domain generalization addresses domain shift in real-world applications. Most approaches adopt a domain angle, seeking invariant representation across domains by aligning their marginal distributions, irrespective of individual classes, naturally leading to insufficient exploration of discriminative information. Switching to a class angle, we find that multiple domain-related peaks or clusters within the same individual classes must emerge due to distribution shift. In other words, marginal alignment does not guarantee conditional alignment, leading to suboptimal generalization. Therefore, we argue that acquiring discriminative generalization between classes within domains is crucial. In contrast to seeking distribution alignment, we endeavor to safeguard domain-related between-class discrimination. To this end, we devise a novel Conjugate Consistent Enhanced Module, namely Con2EM, based on a distribution over domains, i.e., a meta-distribution. Specifically, we employ a novel distribution-level Universum strategy to generate supplementary diverse domain-related class-conditional distributions, thereby enhancing generalization. This allows us to resample from these generated distributions to provide feedback to the primordial instance-level classifier, further improving its adaptability to the target-agnostic. To ensure generation accuracy, we establish an additional distribution-level classifier to regularize these conditional distributions. Extensive experiments have been conducted to demonstrate its effectiveness and low computational cost compared to SOTAs.