Continual Normalization: Rethinking Batch Normalization for Online Continual Learning
This addresses a critical bottleneck in online continual learning for AI systems that need to adapt to non-i.i.d. data streams, offering an incremental improvement over existing normalization methods.
The paper tackles the problem of Batch Normalization (BN) causing catastrophic forgetting in online continual learning due to biased normalization statistics, and proposes Continual Normalization (CN) as a replacement that provides substantial performance improvements across various algorithms and scenarios.
Existing continual learning methods use Batch Normalization (BN) to facilitate training and improve generalization across tasks. However, the non-i.i.d and non-stationary nature of continual learning data, especially in the online setting, amplify the discrepancy between training and testing in BN and hinder the performance of older tasks. In this work, we study the cross-task normalization effect of BN in online continual learning where BN normalizes the testing data using moments biased towards the current task, resulting in higher catastrophic forgetting. This limitation motivates us to propose a simple yet effective method that we call Continual Normalization (CN) to facilitate training similar to BN while mitigating its negative effect. Extensive experiments on different continual learning algorithms and online scenarios show that CN is a direct replacement for BN and can provide substantial performance improvements. Our implementation is available at \url{https://github.com/phquang/Continual-Normalization}.