Big Transfer (BiT): General Visual Representation Learning

Alexander KolesnikovLucas BeyerXiaohua ZhaiJoan PuigcerverJessica YungSylvain GellyNeil Houlsby

   Papers with code   Abstract  PDF

Transfer of pre-trained representations improves sample efficiency and simplifies hyperparameter tuning when training deep neural networks for vision. We revisit the paradigm of pre-training on large supervised datasets and fine-tuning the model on a target task... (read more)

Benchmarked Models

RANK
MODEL
REPO
CODE RESULT
PAPER RESULT
ε-REPRODUCED
BUILD