TY - GEN
T1 - Decorrelated Batch Normalization
AU - Huangi, Lei
AU - Yang, Dawei
AU - Lang, Bo
AU - Deng, Jia
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/12/14
Y1 - 2018/12/14
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85061172524&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85061172524&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2018.00089
DO - 10.1109/CVPR.2018.00089
M3 - Conference contribution
AN - SCOPUS:85061172524
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 791
EP - 800
BT - Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
PB - IEEE Computer Society
T2 - 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
Y2 - 18 June 2018 through 22 June 2018
ER -