2 papers
cs.CV2025
Rethinking the Sample Relations for Few-Shot Classification
Guowei Yin, Sheng Huang, Luwen Huangfu +2
Feature quality is paramount for classification performance, particularly in few-shot scenarios. Contrastive learning, a widely adopted technique for enhancing feature quality, lev…
cs.CV2024
Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology
Wenhao Tang, Fengtao Zhou, Sheng Huang +3
Multiple instance learning (MIL) is the most widely used framework in computational pathology, encompassing sub-typing, diagnosis, prognosis, and more. However, the existing MIL pa…