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, \emph{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. This strategy accommodates sufficient generalizable features and facilitates within-class variations. Extensive experiments on four benchmark datasets corroborate the efficacy of our method.

翻译：领域泛化（Domain Generalization, DG）旨在开发具有强大泛化能力同时保持优异可分性的稳健模型。然而，关键性的DG技术往往通过学习域不变表示来提升特征泛化能力，却无意中忽略了特征可分性。一方面，同时实现特征的泛化能力与可分性是一项复杂挑战，常伴随内在矛盾。当域不变特征因包含不稳定因素（即虚假相关性）而呈现降低的可分性时，这一挑战尤为显著。另一方面，主流的域不变方法可归类为类别级对齐，这种方法容易丢弃具有强大泛化能力的关键特征，并缩小类内差异。为克服这些障碍，我们从新视角重新思考领域泛化，使特征同时具备强大的可分性与稳健的泛化能力，并提出一种新颖框架——判别性微观分布对齐（Discriminative Microscopic Distribution Alignment, DMDA）。DMDA包含两个核心组件：选择性通道剪枝（Selective Channel Pruning, SCP）与微观级分布对齐（Micro-level Distribution Alignment, MDA）。具体而言，SCP试图削减神经网络中的冗余性，优先关注有利于准确分类的稳定属性。该方法缓解了虚假域不变性的负面影响，并增强了特征可分性。此外，MDA强调每个类别内的微观级对齐，超越了单纯的类别级对齐。该策略容纳了足够可泛化的特征并促进了类内变异。在四个基准数据集上的大量实验验证了我们方法的有效性。