Batch normalization is a key component of most image classification models, but it has many undesirable properties stemming from its dependence on the batch size and interactions between examples. Although recent work has succeeded in training deep ResNets without normalization layers, these models do not match the test accuracies of the best batch-normalized networks, and are often unstable for large learning rates or strong data augmentations... (read more)
PDF
Ranked #3 on
Image Classification
on ImageNet
(using extra training data)
METHOD | TYPE | |
---|---|---|
![]() |
Activation Functions | |
![]() |
Optimization |