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.
Proxy Robustness in Vision Language Models is Effortlessly Transferable
Chongqing Key Laboratory of Bio-perception(重庆生物感知实验室);Multimodal Intelligent Information Processing, Chongqing University, Chongqing 401331, China(多模态智能信息处理,重庆大学,重庆401331,中国);School of Microelectronics(微电子学院);Communication Engineering, Chongqing University, Chongqing 401331, China(通信工程,重庆大学,重庆401331,中国);School of Data Science, Lingnan University, Hong Kong(数据科学学院,岭南大学,香港)
Learning to Learn with Variational Information Bottleneck for Domain Generalization
University of Amsterdam(阿姆斯特丹大学);Nankai University(南开大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);Duke University(杜克大学);Inception Institute of Artificial Intelligence(起源人工智能研究院)
CIBR: Cross-modal Information Bottleneck Regularization for Robust CLIP Generalization
Aerospace Information Research Institute, Chinese Academy of Sciences(中国科学院空天信息创新研究院);University of Alabama at Birmingham(阿拉巴马大学伯明翰分校);Harvard Medical School(哈佛医学院);Wuhan University(武汉大学);Bowling Green State University(鲍灵格林州立大学);University of California, Irvine(加州大学欧文分校);School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences(中国科学院大学电子电气与通信工程学院)
Learning Decomposable and Debiased Representations via Attribute-Centric Information Bottlenecks
School of Computing and Augmented Intelligence(计算与增强智能学院);Arizona State University(亚利桑那州立大学);School of Arts, Media and Engineering(艺术、媒体与工程学院);School of Life Sciences(生命科学学院)
提出去偏框架 Debiasing Global Workspace,利用基于注意力的信息瓶颈学习可分解的内在与偏置属性组合表示,提升模型分布外泛化能力并区分内在与偏置特征。