Scholarlink

<p>Domain generalization (DG) ensures machine learning models remain robust against distribution shifts from source to unseen target domains. DG research has evolved from small-scale models tailored with specialized loss functions, to parameter-efficient fine-tuning of moderately large models, and now toward leveraging large multimodal models (LMMs) that are pre-trained on vast datasets. Despite their zero-shot capabilities, LMMs face challenges in adapting to specialized scenarios (e.g., healthcare) without costly retraining. In this work, we propose <b>ICL-DG</b>, a novel DG framework that integrates <i>in-context learning</i> (ICL) to help adaptability under distribution shifts. We theoretically conceptualize demonstration selection with a Bayesian inference perspective as the process of providing effective conditional priors. To realize this, we introduce the class-conditioned contrastive invariance (CCI) principle, which reshapes the embedding space so that same-class samples from different domains cluster together while maintaining separation between distinct classes. This approach enables the selection of demonstrations based on stable class-level semantics rather than domain-specific artifacts, thereby guiding LMMs under distribution shifts without parameter updates. Empirical evaluations on four benchmarks, including Camelyon17 and HAM10000, demonstrate the efficacy of ICL-DG, with improvements of 34.2% and 16.9% in 7-shot accuracy over the zero-shot baseline, respectively. These results highlight the potential of pairing ICL with invariant demonstration selection to advance LMMs-based DG, particularly in high-stakes domains like healthcare.Our code is available at: <a href="https://github.com/jameszhou-gl/ICL-DG.">https://github.com/jameszhou-gl/ICL-DG.</a></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

From Small to Large: In-Context Learning as a New Paradigm for Domain Generalization

  • 期刊论文

  • 发表日期：

    2025年12月23日

查看全文
  • Guanglin Zhou,
  • Zhongyi Han,
  • Shaoan Xie,
  • Shiming Chen,
  • Biwei Huang,
  • Liming Zhu,
  • Xin Gao,
  • Lina Yao,
  • Salman Khan

摘要

Domain generalization (DG) ensures machine learning models remain robust against distribution shifts from source to unseen target domains. DG research has evolved from small-scale models tailored with specialized loss functions, to parameter-efficient fine-tuning of moderately large models, and now toward leveraging large multimodal models (LMMs) that are pre-trained on vast datasets. Despite their zero-shot capabilities, LMMs face challenges in adapting to specialized scenarios (e.g., healthcare) without costly retraining. In this work, we propose ICL-DG, a novel DG framework that integrates in-context learning (ICL) to help adaptability under distribution shifts. We theoretically conceptualize demonstration selection with a Bayesian inference perspective as the process of providing effective conditional priors. To realize this, we introduce the class-conditioned contrastive invariance (CCI) principle, which reshapes the embedding space so that same-class samples from different domains cluster together while maintaining separation between distinct classes. This approach enables the selection of demonstrations based on stable class-level semantics rather than domain-specific artifacts, thereby guiding LMMs under distribution shifts without parameter updates. Empirical evaluations on four benchmarks, including Camelyon17 and HAM10000, demonstrate the efficacy of ICL-DG, with improvements of 34.2% and 16.9% in 7-shot accuracy over the zero-shot baseline, respectively. These results highlight the potential of pairing ICL with invariant demonstration selection to advance LMMs-based DG, particularly in high-stakes domains like healthcare.Our code is available at: https://github.com/jameszhou-gl/ICL-DG.