MUSE: 通过精确和多样的语义提升少样本全滑片图像分类
MUSE: Harnessing Precise and Diverse Semantics for Few-Shot Whole Slide Image Classification
AI总结:
MUSE通过样本层面的细粒度语义增强和随机多视图生成,提升少样本全滑片图像分类的性能和鲁棒性。
摘要:
在计算病理学中,少样本全滑片图像分类主要受到专家标注滑片极度稀缺的限制。最近的视觉-语言方法结合了由大型语言模型生成的文本语义,但将这些描述视为在所有样本中共享的静态类级先验,缺乏样本层面的细化。这限制了视觉-语义对齐的多样性和精确性,阻碍了在有限监督下的泛化能力。为了解决这一问题,我们提出了随机多视图语义增强(MUSE)框架,该框架首先通过样本层面的适应来提升语义精度,然后通过检索增强的多视图生成来增强语义丰富性。具体来说,MUSE引入了样本层面的细粒度语义增强(SFSE),通过基于MoE的自适应视觉-语义交互为每个样本生成细粒度的语义先验。在该先验的引导下,随机多视图模型优化(SMMO)为每个类别构建一个包含多样病理描述的LLM生成的知识库,然后在训练过程中检索并随机整合多个匹配的文本视图。这些动态选择的文本作为丰富的语义监督,用于随机优化视觉-语言模型,促进鲁棒性和缓解过拟合。在三个基准WSI数据集上的实验表明,MUSE在少样本设置下始终优于现有的视觉-语言基线,证明了有效的少样本病理学习不仅需要更丰富的语义来源,还需要其主动和样本感知的语义优化。我们的代码可在:https://github.com/JiahaoXu-god/CVPR2026_MUSE获取。
英文摘要:
In computational pathology, few-shot whole slide image classification is primarily driven by the extreme scarcity of expert-labeled slides. Recent vision-language methods incorporate textual semantics generated by large language models, but treat these descriptions as static class-level priors that are shared across all samples and lack sample-wise refinement. This limits both the diversity and precision of visual-semantic alignment, hindering generalization under limited supervision. To overcome this, we propose the stochastic MUlti-view Semantic Enhancement (MUSE), a framework that first refines semantic precision via sample-wise adaptation and then enhances semantic richness through retrieval-augmented multi-view generation. Specifically, MUSE introduces Sample-wise Fine-grained Semantic Enhancement (SFSE), which yields a fine-grained semantic prior for each sample through MoE-based adaptive visual-semantic interaction. Guided by this prior, Stochastic Multi-view Model Optimization (SMMO) constructs an LLM-generated knowledge base of diverse pathological descriptions per class, then retrieves and stochastically integrates multiple matched textual views during training. These dynamically selected texts serve as enriched semantic supervisions to stochastically optimize the vision-language model, promoting robustness and mitigating overfitting. Experiments on three benchmark WSI datasets show that MUSE consistently outperforms existing vision-language baselines in few-shot settings, demonstrating that effective few-shot pathology learning requires not only richer semantic sources but also their active and sample-aware semantic optimization. Our code is available at: https://github.com/JiahaoXu-god/CVPR2026_MUSE.
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。