AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

MUSE: Harnessing Precise and Diverse Semantics for Few-Shot Whole Slide Image Classification

Jiahao Xu, Sheng Huang, Xin Zhang, Zhixiong Nan, Jiajun Dong, Nankun Mu

CVPR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Open-vocabulary alignment from VLMs · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add SMMO stochastic multi-view optimization (ablation)MUSE (BM+TI) · CAMELYON 4-shotACC: 65.13 -> 71.18Improved
add SFSE fine-grained semantic enhancement (ablation)BM + TI · CAMELYON 4-shotACC: 65.13 -> 65.16No clear effect
add SFSE on top of TI + SMMO (ablation)MUSE · CAMELYON 4-shotACC: 71.18 -> 74.86Improved
add traditional text-patch interaction to base MIL (ablation)Base MIL · CAMELYON 16-shotACC: 82.37 -> 86.61Improved
use cosine retrieval instead of random selection (ablation)SMMO · CAMELYON 4-shotACC: 72.23 -> 74.86Improved
use cosine instead of L2 or random retrieval (ablation)SMMO · CAMELYON 8-shotACC: 84.20/84.49 -> 84.01Mixed
use stochastic optimization instead of multi-mean (ablation)SMMO · CAMELYON 4-shotACC: 70.33 -> 74.86Improved
use stochastic instead of multi-mean optimization (ablation)SMMO · CAMELYON 8-shotACC: 84.08 -> 84.01No clear effect
build knowledge base with Qwen2-7B instead of Llama-3.2-1B (ablation)MUSE · CAMELYON 4-shotACC: 70.44 -> 74.86Improved
build knowledge base with Qwen2-7B (ablation)MUSE · CAMELYON 8-shotACC: 84.94 -> 84.01Mixed
use MUSE instead of FOCUSMUSE vs FOCUS · CAMELYON 4-shotACC: 68.13 -> 74.86Improved
use MUSE instead of FOCUSMUSE vs FOCUS · TCGA-NSCLC 4-shotACC: 79.14 -> 79.90Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy