Domain-Specific Batch Normalization for Unsupervised Domain Adaptation

TL;DR

This paper introduces a domain-specific batch normalization approach for unsupervised domain adaptation in deep neural networks, improving performance by customizing normalization layers for each domain while sharing other model parameters.

Contribution

The authors propose a two-stage algorithm that integrates domain-specific batch normalization into existing adaptation methods, extending to multiple source domains and achieving state-of-the-art results.

Findings

Achieves state-of-the-art accuracy on benchmark datasets.

Effective extension to multi-source domain adaptation.

Compatible with existing deep domain adaptation techniques.

Abstract

We propose a novel unsupervised domain adaptation framework based on domain-specific batch normalization in deep neural networks. We aim to adapt to both domains by specializing batch normalization layers in convolutional neural networks while allowing them to share all other model parameters, which is realized by a two-stage algorithm. In the first stage, we estimate pseudo-labels for the examples in the target domain using an external unsupervised domain adaptation algorithm---for example, MSTN or CPUA---integrating the proposed domain-specific batch normalization. The second stage learns the final models using a multi-task classification loss for the source and target domains. Note that the two domains have separate batch normalization layers in both stages. Our framework can be easily incorporated into the domain adaptation techniques based on deep neural networks with batch normalization layers. We also present that our approach can be extended to the problem with multiple source domains. The proposed algorithm is evaluated on multiple benchmark datasets and achieves the state-of-the-art accuracy in the standard setting and the multi-source domain adaption scenario.