Differentiable Dynamic Normalization for Learning Deep Representation
Abstract
This work presents Dynamic Normalization (DN), which is able to learn arbitrary normalization operations for different convolutional layers in a deep ConvNet. Unlike existing normalization approaches that predefined computations of the statistics (mean and variance), DN learns to estimate them. DN has several appealing benefits. First, it adapts to various networks, tasks, and batch sizes. Second, it can be easily implemented and trained in a differentiable end-to-end manner with merely small number of parameters. Third, its matrix formulation represents a wide range of normalization methods, shedding light on analyzing them theoretically. Extensive studies show that DN outperforms its counterparts in CIFAR10 and ImageNet.
Cite
Text
Luo et al. "Differentiable Dynamic Normalization for Learning Deep Representation." International Conference on Machine Learning, 2019.Markdown
[Luo et al. "Differentiable Dynamic Normalization for Learning Deep Representation." International Conference on Machine Learning, 2019.](https://mlanthology.org/icml/2019/luo2019icml-differentiable/)BibTeX
@inproceedings{luo2019icml-differentiable,
title = {{Differentiable Dynamic Normalization for Learning Deep Representation}},
author = {Luo, Ping and Zhanglin, Peng and Wenqi, Shao and Ruimao, Zhang and Jiamin, Ren and Lingyun, Wu},
booktitle = {International Conference on Machine Learning},
year = {2019},
pages = {4203-4211},
volume = {97},
url = {https://mlanthology.org/icml/2019/luo2019icml-differentiable/}
}