Reciprocal Normalization for Domain Adaptation

TL;DR

This paper introduces Reciprocal Normalization (RN), a novel normalization technique that leverages cross-domain relations to improve unsupervised domain adaptation performance in deep neural networks.

Contribution

The paper proposes Reciprocal Normalization, a new method that enhances domain adaptation by modeling cross-domain feature relations, outperforming existing normalization techniques.

Findings

RN outperforms existing normalization methods significantly.

RN improves the performance of state-of-the-art domain adaptation approaches.

RN is easy to integrate into existing models.

Abstract

Batch normalization (BN) is widely used in modern deep neural networks, which has been shown to represent the domain-related knowledge, and thus is ineffective for cross-domain tasks like unsupervised domain adaptation (UDA). Existing BN variant methods aggregate source and target domain knowledge in the same channel in normalization module. However, the misalignment between the features of corresponding channels across domains often leads to a sub-optimal transferability. In this paper, we exploit the cross-domain relation and propose a novel normalization method, Reciprocal Normalization (RN). Specifically, RN first presents a Reciprocal Compensation (RC) module to acquire the compensatory for each channel in both domains based on the cross-domain channel-wise correlation. Then RN develops a Reciprocal Aggregation (RA) module to adaptively aggregate the feature with its cross-domain compensatory components. As an alternative to BN, RN is more suitable for UDA problems and can be easily integrated into popular domain adaptation methods. Experiments show that the proposed RN outperforms existing normalization counterparts by a large margin and helps state-of-the-art adaptation approaches achieve better results. The source code is available on https://github.com/Openning07/reciprocal-normalization-for-DA.