Adversarially Adaptive Normalization for Single Domain Generalization

by   Xinjie Fan, et al.

Single domain generalization aims to learn a model that performs well on many unseen domains with only one domain data for training. Existing works focus on studying the adversarial domain augmentation (ADA) to improve the model's generalization capability. The impact on domain generalization of the statistics of normalization layers is still underinvestigated. In this paper, we propose a generic normalization approach, adaptive standardization and rescaling normalization (ASR-Norm), to complement the missing part in previous works. ASR-Norm learns both the standardization and rescaling statistics via neural networks. This new form of normalization can be viewed as a generic form of the traditional normalizations. When trained with ADA, the statistics in ASR-Norm are learned to be adaptive to the data coming from different domains, and hence improves the model generalization performance across domains, especially on the target domain with large discrepancy from the source domain. The experimental results show that ASR-Norm can bring consistent improvement to the state-of-the-art ADA approaches by 1.6 Digits, CIFAR-10-C, and PACS benchmarks, respectively. As a generic tool, the improvement introduced by ASR-Norm is agnostic to the choice of ADA methods.


page 4

page 12


A Domain Agnostic Normalization Layer for Unsupervised Adversarial Domain Adaptation

We propose a normalization layer for unsupervised domain adaption in sem...

SelfNorm and CrossNorm for Out-of-Distribution Robustness

Normalization techniques are crucial in stabilizing and accelerating the...

TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification

Domain generalizable person re-identification aims to apply a trained mo...

Learning to Optimize Domain Specific Normalization for Domain Generalization

We propose a simple but effective multi-source domain generalization tec...

META: Mimicking Embedding via oThers' Aggregation for Generalizable Person Re-identification

Domain generalizable (DG) person re-identification (ReID) aims to test a...

Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net

Convolutional neural networks (CNNs) have achieved great successes in ma...

Switchable Whitening for Deep Representation Learning

Normalization methods are essential components in convolutional neural n...