FFM-CP: Cross-Backbone Fusion of Vision-Language Foundation Models for Few-Shot Computational Pathology
It is suggested that combining complementary pretrained representations can improve histopathological classification when annotations are limited, and FFM-CP achieves higher mean macro-F1 than the strongest individually adapted member of each fused set in 50 of 54 comparisons.
Anh-Tien Nguyen, Trung DQ. Dang, N. T. Diep et al.
· 0 citations