arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2607.01657cs.CV
收藏

基于文本锚定信息瓶颈的域泛化

Domain Generalization via Text-Anchored Information Bottleneck

Seoul National University(首尔大学)

Eunyi Lyou, Yunjeong Choi, Junho Lee, Joonseok Lee

AI总结:

提出通过语言嵌入空间作为信息瓶颈来抑制视觉表征中的虚假线索,从而提升域泛化性能,实验表明该方法达到最新最优水平。

摘要:

视觉识别模型在新环境中部署时常常失败。域泛化(DG)通过学习对环境特定变化保持不变的表示来解决这一问题。最近的方法越来越依赖大型视觉-语言模型,假设保留其富有表现力的视觉表示能提高鲁棒性。然而,我们表明这种视觉表现力反而可能传播虚假线索,将表示与训练环境绑定,阻碍不变学习。因此,我们放弃视觉引导,转而将语言嵌入空间作为域不变性的主要来源,自然地充当信息瓶颈,保留核心语义同时抑制域特定变化。跨多种骨干网络的广泛实验展示了最先进的性能,并进一步分析了什么使引导对鲁棒泛化有效。这些发现将DG的关注点从改进表示转向设计强制不变性的监督。

英文摘要:

Visual recognition models often fail when deployed in new environments. Domain Generalization (DG) addresses this by learning representations that remain invariant to environment-specific variations. Recent approaches increasingly rely on large vision-language models, assuming that preserving their expressive visual representations improves robustness. However, we show that such visual expressiveness can instead propagate spurious cues that tie representations to the training environments, hindering invariant learning. We therefore discard visual guidance and instead treat the language embedding space as the primary source of domain invariance, naturally acting as an information bottleneck that preserves core semantics while suppressing domain-specific variations. Extensive experiments across diverse backbones exhibit state-of-the-art performance and further analyze what makes guidance effective for robust generalization. These findings shift the focus of DG from improving representations to designing supervision that enforces invariance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑