An Empirical Study of Batch Normalization and Group Normalization in Conditional Computation
This work addresses the problem of improving generalization in conditional computation tasks for machine learning practitioners, but it is incremental as it builds on existing normalization methods.
The study compared conditional group normalization with conditional batch normalization across visual question answering, few-shot learning, and conditional image generation tasks, finding that conditional group normalization improved generalization in some domains.
Batch normalization has been widely used to improve optimization in deep neural networks. While the uncertainty in batch statistics can act as a regularizer, using these dataset statistics specific to the training set impairs generalization in certain tasks. Recently, alternative methods for normalizing feature activations in neural networks have been proposed. Among them, group normalization has been shown to yield similar, in some domains even superior performance to batch normalization. All these methods utilize a learned affine transformation after the normalization operation to increase representational power. Methods used in conditional computation define the parameters of these transformations as learnable functions of conditioning information. In this work, we study whether and where the conditional formulation of group normalization can improve generalization compared to conditional batch normalization. We evaluate performances on the tasks of visual question answering, few-shot learning, and conditional image generation.