Research map / Learning theory and algorithms / Clustering
One Slide, Many Views: Unifying Complementary Foundation Model Perspectives for WSI Analysis
Yihui WANG, Yingxue Xu, Shu Yang, Yequan Bie, Jiabo MA, Fengtao Zhou, Hao Chen
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add UNI view (ablation) | MV-MIL · Molecular prediction average | AUC: 0.7930 -> 0.8008 | Improved |
| add CONCH view (ablation) | MV-MIL · Molecular prediction average | AUC: 0.7911 -> 0.8008 | Improved |
| add Virchow2 view (ablation) | MV-MIL · Molecular prediction average | AUC: 0.7866 -> 0.8008 | Improved |
| add H-Optimus-1 view (ablation) | MV-MIL · Molecular prediction average | AUC: 0.7779 -> 0.8008 | Improved |
| increase number of FM views from one to two (ablation) | MV-MIL · Molecular prediction average | AUC: 0.7821 -> 0.7897 | Improved |
| increase number of FM views from two to three (ablation) | MV-MIL · Molecular prediction average | AUC: 0.7897 -> 0.7929 | Improved |
| increase number of FM views from three to four (ablation) | MV-MIL · Molecular prediction average | AUC: 0.7929 -> 0.8008 | Improved |
| add concatenated branch to specific branches (ablation) | MV-MIL prediction head · Molecular prediction average | AUC: 0.7834 -> 0.7900 | Improved |
| add shared branch to concat and specific branches (ablation) | MV-MIL prediction head · Molecular prediction average | AUC: 0.7900 -> 0.8008 | Improved |
| add consistency objective (ablation) | MV-MIL · Molecular prediction average | AUC: 0.7902 -> 0.8008 | Improved |
| add specificity objective (ablation) | MV-MIL · Molecular prediction average | AUC: 0.7893 -> 0.8008 | Improved |
| replace Naive Ensemble with MV-MIL multi-view disentanglement | multi-FM ensembling · Molecular prediction average | AUC: 0.7811 -> 0.8008 | Improved |
Closest papers by meaning
- Boosting Multiple Instance Learning Models for Whole Slide Image Classification: A Model-Agnostic Framework Based on Counterfactual Inference (AAAI 2024 · similarity 0.87)
- M3amba: Memory Mamba is All You Need for Whole Slide Image Classification (CVPR 2025 · similarity 0.85)
- CaMIL: Causal Multiple Instance Learning for Whole Slide Image Classification (AAAI 2024 · similarity 0.84)
- MExD: An Expert-Infused Diffusion Model for Whole-Slide Image Classification (CVPR 2025 · similarity 0.84)
- OODML: Whole Slide Image Classification Meets Online Pseudo-Supervision and Dynamic Mutual Learning (AAAI 2025 · similarity 0.84)
- FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide Image Classification (NeurIPS 2024 · similarity 0.84)
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.
