Decorrelated Batch Normalization
This work addresses the optimization and generalization challenges in deep learning for researchers and practitioners, representing an incremental improvement over Batch Normalization.
The paper tackles the problem of accelerating deep model training by proposing Decorrelated Batch Normalization (DBN), which whitens activations instead of just centering and scaling them, resulting in improved optimization efficiency and generalization, with consistent accuracy gains on residual networks across CIFAR-10, CIFAR-100, and ImageNet datasets.
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.