2019.12.17 note

2019.12.17 note

Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks

Batch Normalization (BN) is a highly successful and widely used batch dependent training method. Its use of mini-batch statistics to normalize the activations introduces dependence between samples, which can hurt the training if the mini-batch size is too small, or if the samples are correlated. Several alternatives, such as Batch Renormalization and Group Normalization (GN), have been proposed to address these issues. However, they either do not match the performance of BN for large batches, or still exhibit degradation in performance for smaller batches, or introduce artificial constraints on the model architecture. In this paper we propose the Filter Response Normalization (FRN) layer, a novel combination of a normalization and an activation function, that can be used as a drop-in replacement for other normalizations and activations.

Orthogonal Convolutional Neural Networks

They propose orthogonal convolutions as regularizations in CNNs and benchmark its effect on various tasks.