Contrastive fine-tuning against stain and scanner bias improves robustness and downstream performance across pathology foundation models
cs.CV
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/bioptimus/releases
Project page: https://micslab.github.io/thunder/leaderboards
Terminology
Sources
- Phikon-v2, A large and public feature extractor for biomarker prediction
- Robustifying pathology foundation models via fine-tuning
- OpenMidnight: Closing the Performance Gap Between Open and Proprietary Pathology Foundation Models
- Scanner-Induced Domain Shifts Undermine the Robustness of Pathology Foundation Models
- Representation Learning with Contrastive Predictive Coding
- Accelerating Data Processing and Benchmarking of AI Models for Pathology
- Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs