Scholarlink

<p>Domain generalization addresses <i>domain shift</i> in real-world applications. Most methods adopt <i>a domain angle</i>, seeking invariant representation across domains by aligning their marginal distributions, irrespective of individual classes, naturally leading to insufficient exploration of discriminative information. Switching to <i>a class angle</i>, 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 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 demonstrate its effectiveness and low computational cost compared to recent strong competitors.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

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

  • 期刊论文

  • 发表日期：

    2026年5月23日

查看全文
  • Meng Cao,
  • Songcan Chen

摘要

Domain generalization addresses domain shift in real-world applications. Most methods 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 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 demonstrate its effectiveness and low computational cost compared to recent strong competitors.