Preprint
Aug 2026
DistillPath: An Efficient 22M Distilled Pathology Encoder Approaching Large Foundation Model Performance
DistillPath-KS16 is presented, which starts from the existing 22M kaiko ViT-S/16 encoder and improves it by distilling from released pathology encoders used as frozen teachers, needing neither their DINO nor iBOT pretraining heads nor a billion-tile corpus.
Ramon Kaspar, Andrey Ignatov, Valentina Boeva
· 2 citations