Adversarially Adaptive Normalization for Single Domain Generalization
| Autor: | Mingyuan Zhou, Qifei Wang, Feng Yang, Xinjie Fan, Junjie Ke, Boqing Gong |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Normalization (statistics)
FOS: Computer and information sciences Theoretical computer science Artificial neural network Computer science Generalization business.industry Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology 030218 nuclear medicine & medical imaging Domain (software engineering) Data modeling 03 medical and health sciences 0302 clinical medicine Adaptive system 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business Focus (optics) Complement (set theory) |
| Zdroj: | CVPR |
| Popis: | 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%, 2.7%, and 6.3% averagely on the 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. CVPR 2021 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|