Search Results for author:
Found 3 papers, 1 papers with code
DINO as a von Mises-Fisher mixture model
With this interpretation, DINO assumes equal precision for all components when the prototypes are also $L^2$-normalized.
DINO as a von Mises-Fisher mixture model
With this interpretation, DINO assumes equal precision for all components when the prototypes are also $L^2$-normalized.
Ranked #24 on
Self-Supervised Image Classification
on ImageNet
Self-Supervised Image Classification
Self-Supervised Learning
+1
Evaluating model calibration in classification
Probabilistic classifiers output a probability distribution on target classes rather than just a class prediction.
