Reciprocal Normalization for Domain Adaptation

12/20/2021
by   Zhiyong Huang, et al.
67

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.

READ FULL TEXT

page 1

page 4

page 10

page 11

research
03/09/2020

Context-Aware Domain Adaptation in Semantic Segmentation

In this paper, we consider the problem of unsupervised domain adaptation...
research
12/28/2020

Improving Unsupervised Domain Adaptation by Reducing Bi-level Feature Redundancy

Reducing feature redundancy has shown beneficial effects for improving t...
research
03/22/2021

A Batch Normalization Classifier for Domain Adaptation

Adapting a model to perform well on unforeseen data outside its training...
research
07/28/2023

AC-Norm: Effective Tuning for Medical Image Analysis via Affine Collaborative Normalization

Driven by the latest trend towards self-supervised learning (SSL), the p...
research
09/20/2023

GraphEcho: Graph-Driven Unsupervised Domain Adaptation for Echocardiogram Video Segmentation

Echocardiogram video segmentation plays an important role in cardiac dis...
research
04/01/2022

An End-to-end Supervised Domain Adaptation Framework for Cross-Domain Change Detection

Existing deep learning-based change detection methods try to elaborately...
research
03/25/2021

On Evolving Attention Towards Domain Adaptation

Towards better unsupervised domain adaptation (UDA). Recently, researche...

Please sign up or login with your details

Forgot password? Click here to reset