Decorrelated Batch Normalization
Abstract
Batch Normalization (BN) is capable of accelerating the training of deep models by centering and scaling activations within mini-batches. In this work, we propose Decorrelated Batch Normalization (DBN), which not just centers and scales activations but whitens them. We explore multiple whitening techniques, and find that PCA whitening causes a problem we call stochastic axis swapping, which is detrimental to learning. We show that ZCA whitening does not suffer from this problem, permitting successful learning. DBN retains the desirable qualities of BN and further improves BN's optimization efficiency and generalization ability. We design comprehensive experiments to show that DBN can improve the performance of BN on multilayer perceptrons and convolutional neural networks. Furthermore, we consistently improve the accuracy of residual networks on CIFAR-10, CIFAR-100, and ImageNet.
Cite
Text
Huang et al. "Decorrelated Batch Normalization." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00089Markdown
[Huang et al. "Decorrelated Batch Normalization." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/huang2018cvpr-decorrelated/) doi:10.1109/CVPR.2018.00089BibTeX
@inproceedings{huang2018cvpr-decorrelated,
title = {{Decorrelated Batch Normalization}},
author = {Huang, Lei and Yang, Dawei and Lang, Bo and Deng, Jia},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2018},
doi = {10.1109/CVPR.2018.00089},
url = {https://mlanthology.org/cvpr/2018/huang2018cvpr-decorrelated/}
}