# MUSE: Harnessing Precise and Diverse Semantics for Few-Shot Whole Slide Image Classification Source: [MUSE: Harnessing Precise and Diverse Semantics for Few-Shot Whole Slide Image Classification]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:00:04.574Z Authors: Jiahao Xu, Sheng Huang, Xin Zhang, Zhixiong Nan, Jiajun Dong, Nankun Mu Published: 2026-02-24T13:17:35.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Weakly Supervised Classification on CAMELYON Few-shot](): Weakly Supervised Classification; CAMELYON Few-shot; Accuracy: 89.7. - [Weakly Supervised Classification on TCGA-NSCLC Few-shot](): Weakly Supervised Classification; TCGA-NSCLC Few-shot; Accuracy: 89.74. - [Weakly Supervised Classification on TCGA-BRCA Few-shot](): Weakly Supervised Classification; TCGA-BRCA Few-shot; Accuracy: 88.23. ## Original sources and implementation [Original paper]() [PDF]()