EXPOSE: Explainable and Domain-Robust Embeddings from Pathology Vision Foundation Models using Sparse Autoencoders

2026-08-28

AI Summary

为解决病理视觉基础模型(VFMs)对域变化敏感的问题，提出使用稀疏自编码器(SAEs)框架EXPOSE，通过识别并抑制域特定成分来提高跨域性能和嵌入鲁棒性。

Abstract

Vision Foundation Models (VFMs) are widely used in computational pathology but remain sensitive to domain shifts arising from variations in staining, tissue preparation, and scanner hardware. A key limitation is that VFM embeddings entangle biological with domain-specific information, hindering cross-domain generalization. We propose Explainable Probing of Cross-Domain Sparse Embeddings (EXPOSE), a framework that uses Sparse Autoencoders (SAEs) as an explainable bottleneck to identify and suppress domain-specific components in VFM embeddings. We train a sparse representation of VFM features, use a linear classifier to identify domain-specific latent dimensions, and mask these features prior to downstream relapse prediction without retraining the backbone model. Experiments on a large prostate cancer dataset with multiple acquisition domains show that SAE features capture both domain- and task-specific information, which are partially disentangled in the latent space. Removing domain-specific features improves cross-domain performance and increases embedding robustness as measured by the Domain Robustness Index (DoRI). Code is available at https://github.com/imsb-uke/expose .

Problem

• Vision Foundation Models
• domain shifts
• cross-domain generalization
• pathology

Innovation

• Sparse Autoencoders
• Cross-Domain Generalization
• Domain-Specific Information Suppression
• Vision Foundation Models