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.

翻译：领域泛化旨在解决现实应用中的领域偏移问题。现有方法大多从领域角度出发，通过对齐不同领域的边缘分布来寻求跨领域的不变表示，这种策略忽略了具体类别信息，自然导致对判别性信息探索不足。转向类别角度分析，我们发现由于分布偏移的存在，同一类别内部必然会出现多个与领域相关的峰值或聚类簇。换言之，边缘分布对齐并不能保证条件分布对齐，从而导致次优的泛化性能。因此，我们认为获取领域内部类别间的判别性泛化能力至关重要。与追求分布对齐不同，我们致力于保护领域相关的类间判别特性。为此，我们基于领域上的分布（即元分布）设计了一种新颖的共轭一致性增强模块（Con2EM）。具体而言，我们采用一种新颖的分布级Universum策略来生成补充性的多样化领域相关类条件分布，从而增强泛化能力。这使得我们可以从这些生成分布中重采样，为原始实例级分类器提供反馈，进一步提升其对目标不可知场景的适应能力。为确保生成准确性，我们额外建立了一个分布级分类器来正则化这些条件分布。大量实验证明，相较于现有最优方法，本方法在保持较低计算成本的同时具有显著有效性。