AI RESEARCH
Parameter-efficient Prompt Tuning and Hierarchical Textual Guidance for Few-shot Whole Slide Image Classification
arXiv CS.CV
•
ArXi:2603.21504v1 Announce Type: new Whole Slide Images (WSIs) are giga-pixel in scale and are typically partitioned into small instances in WSI classification pipelines for computational feasibility. However, obtaining extensive instance level annotations is costly, making few-shot weakly supervised WSI classification (FSWC) crucial for learning from limited slide-level labels. Recently, pre-trained vision-language models (VLMs) have been adopted in FSWC, yet they exhibit several limitations.