Rethinking "Batch" in BatchNorm
arXiv:2105.07576
Abstract
BatchNorm is a critical building block in modern convolutional neural networks. Its unique property of operating on "batches" instead of individual samples introduces significantly different behaviors from most other operations in deep learning. As a result, it leads to many hidden caveats that can negatively impact model's performance in subtle ways. This paper thoroughly reviews such problems in visual recognition tasks, and shows that a key to address them is to rethink different choices in the concept of "batch" in BatchNorm. By presenting these caveats and their mitigations, we hope this review can help researchers use BatchNorm more effectively.
Tech report
References in corpus (5)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- High-Performance Large-Scale Image Recognition Without Normalization
- Domain-Specific Batch Normalization for Unsupervised Domain Adaptation
- Towards an Adversarially Robust Normalization Approach
- Momentum^2 Teacher: Momentum Teacher with Momentum Statistics for Self-Supervised Learning