Group Whitening: Balancing Learning Efficiency and Representational Capacity

by   Lei Huang, et al.

Batch normalization (BN) is an important technique commonly incorporated into deep learning models to perform standardization within mini-batches. The merits of BN in improving model's learning efficiency can be further amplified by applying whitening, while its drawbacks in estimating population statistics for inference can be avoided through group normalization (GN). This paper proposes group whitening (GW), which elaborately exploits the advantages of the whitening operation and avoids the disadvantages of normalization within mini-batches. Specifically, GW divides the neurons of a sample into groups for standardization, like GN, and then further decorrelates the groups. In addition, we quantitatively analyze the constraint imposed by normalization, and show how the batch size (group number) affects the performance of batch (group) normalized networks, from the perspective of model's representational capacity. This analysis provides theoretical guidance for applying GW in practice. Finally, we apply the proposed GW to ResNet and ResNeXt architectures and conduct experiments on the ImageNet and COCO benchmarks. Results show that GW consistently improves the performance of different architectures, with absolute gains of 1.02% ∼ 1.49% in top-1 accuracy on ImageNet and 1.82% ∼ 3.21% in bounding box AP on COCO.


page 1

page 2

page 3

page 4


Delving into the Estimation Shift of Batch Normalization in a Network

Batch normalization (BN) is a milestone technique in deep learning. It n...

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 de...

Group Normalization

Batch Normalization (BN) is a milestone technique in the development of ...

An Investigation into the Stochasticity of Batch Whitening

Batch Normalization (BN) is extensively employed in various network arch...

Iterative Normalization: Beyond Standardization towards Efficient Whitening

Batch Normalization (BN) is ubiquitously employed for accelerating neura...

Making EfficientNet More Efficient: Exploring Batch-Independent Normalization, Group Convolutions and Reduced Resolution Training

Much recent research has been dedicated to improving the efficiency of t...

Kernel Normalized Convolutional Networks

Existing deep convolutional neural network (CNN) architectures frequentl...