Domain Generalization via Text-Anchored Information Bottleneck

• URL: http://arxiv.org/abs/2607.01657v1
• Date: Thu, 02 Jul 2026 03:31:34 GMT
• Title: Domain Generalization via Text-Anchored Information Bottleneck
• Abstract summary: Domain Generalization (DG) addresses this by learning representations that remain invariant to environment-specific variations.<n>Recent approaches rely on large vision-language models, assuming that preserving their expressive visual representations improves robustness.<n>We show that such visual robustness can instead propagate spurious cues that tie representations to the training environments, hindering invariant learning.
• Score: 25.417894587788208
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Open-Vocabulary Domain Generalization in Urban-Scene Segmentation [83.15573353963235]
  Domain Generalization in Semantic Domain (DG-SS) aims to enable segmentation models to perform robustly in unseen environments.<n>Recent progress in Vision-Language Models (VLMs) has advanced Open-Vocabulary Semantic (OV-SS) by enabling models to recognize a broader range of concepts.<n>Yet, these models remain sensitive to domain shifts and struggle to maintain robustness when deployed in unseen environments.<n>We propose S2-Corr, a state-space-driven text-image correlation refinement mechanism that produces more consistent text-image correlations under distribution changes.
  arXiv  Detail & Related papers  (2026-02-21T14:32:27Z)
• Unpaired Image-to-Image Translation via a Self-Supervised Semantic Bridge [59.247871132422006]
  Adversarial diffusion and diffusion-inversion methods have advanced unpaired image-to-image translation, but each faces key limitations.<n>We propose the Self-Supervised Semantic Bridge ( SSB), a versatile framework that integrates external semantic priors into diffusion bridge models.<n>Our key idea is to leverage self-supervised visual encoders to learn representations that are invariant to appearance changes but capture geometric structure.
  arXiv  Detail & Related papers  (2026-02-18T18:05:00Z)
• Exploiting Domain Properties in Language-Driven Domain Generalization for Semantic Segmentation [16.081767698947186]
  We present a novel domain generalization framework for semantic segmentation, namely Domain-aware Prompt-driven Masked Transformer (DPMFormer)<n> Firstly, we introduce domain-aware prompt learning to facilitate semantic alignment between visual and textual cues.<n>To capture various domain-specific properties with a single source dataset, we propose domain-aware contrastive learning along with the texture perturbation that diversifies the observable domains.
  arXiv  Detail & Related papers  (2025-12-03T06:58:38Z)
• Prompt Disentanglement via Language Guidance and Representation Alignment for Domain Generalization [75.88719716002014]
  Domain Generalization (DG) seeks to develop a versatile model capable of performing effectively on unseen target domains.<n>Recent advances in pre-trained Visual Foundation Models (VFMs) have demonstrated considerable potential in enhancing the generalization capabilities of deep learning models.<n>We propose addressing this challenge by leveraging the controllable and flexible language prompt of the VFM.
  arXiv  Detail & Related papers  (2025-07-03T03:52:37Z)
• WIDIn: Wording Image for Domain-Invariant Representation in Single-Source Domain Generalization [63.98650220772378]
  We present WIDIn, Wording Images for Domain-Invariant representation, to disentangle discriminative visual representation. We first estimate the language embedding with fine-grained alignment, which can be used to adaptively identify and then remove domain-specific counterpart. We show that WIDIn can be applied to both pretrained vision-language models like CLIP, and separately trained uni-modal models like MoCo and BERT.
  arXiv  Detail & Related papers  (2024-05-28T17:46:27Z)
• Transitive Vision-Language Prompt Learning for Domain Generalization [41.484858946789664]
  The vision-language pre-training has enabled deep models to make a huge step forward in generalizing across unseen domains. However, there are still some issues that an advancement still suffers from trading-off between domain invariance and class separability.
  arXiv  Detail & Related papers  (2024-04-29T14:56:11Z)
• HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain Generalization [69.33162366130887]
  Domain Generalization (DG) endeavors to create machine learning models that excel in unseen scenarios by learning invariant features. We introduce a novel method designed to supplement the model with domain-level and task-specific characteristics. This approach aims to guide the model in more effectively separating invariant features from specific characteristics, thereby boosting the generalization.
  arXiv  Detail & Related papers  (2024-01-18T04:23:21Z)
• TeG-DG: Textually Guided Domain Generalization for Face Anti-Spoofing [8.830873674673828]
  Existing methods are dedicated to extracting domain-invariant features from various training domains. The extracted features inevitably contain residual style feature bias, resulting in inferior generalization performance. We propose the Textually Guided Domain Generalization framework, which can effectively leverage text information for cross-domain alignment.
  arXiv  Detail & Related papers  (2023-11-30T10:13:46Z)
• Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization [113.03189252044773]
  We propose a unified framework, Style-HAllucinated Dual consistEncy learning (SHADE), to handle domain shift in various visual tasks. Our versatile SHADE can significantly enhance the generalization in various visual recognition tasks, including image classification, semantic segmentation and object detection.
  arXiv  Detail & Related papers  (2022-12-18T11:42:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.