Revisiting Batch Normalization For Practical Domain Adaptation

TL;DR

This paper introduces Adaptive Batch Normalization (AdaBN), a simple, parameter-free method that enhances deep neural networks' ability to adapt across different domains without additional components.

Contribution

The paper proposes AdaBN, a novel approach that modulates Batch Normalization statistics for improved domain adaptation, achieving state-of-the-art results with minimal complexity.

Findings

AdaBN improves domain adaptation performance.

It is parameter-free and easy to implement.

Combining AdaBN with other methods enhances results.

Abstract

Deep neural networks (DNN) have shown unprecedented success in various computer vision applications such as image classification and object detection. However, it is still a common annoyance during the training phase, that one has to prepare at least thousands of labeled images to fine-tune a network to a specific domain. Recent study (Tommasi et al. 2015) shows that a DNN has strong dependency towards the training dataset, and the learned features cannot be easily transferred to a different but relevant task without fine-tuning. In this paper, we propose a simple yet powerful remedy, called Adaptive Batch Normalization (AdaBN) to increase the generalization ability of a DNN. By modulating the statistics in all Batch Normalization layers across the network, our approach achieves deep adaptation effect for domain adaptation tasks. In contrary to other deep learning domain adaptation methods, our method does not require additional components, and is parameter-free. It archives state-of-the-art performance despite its surprising simplicity. Furthermore, we demonstrate that our method is complementary with other existing methods. Combining AdaBN with existing domain adaptation treatments may further improve model performance.