Adversarial Bayesian Augmentation for Single-Source Domain Generalization
Authors:
- 1 October 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 11366-11376
Abstract
Generalizing to unseen image domains is a challenging problem primarily due to the lack of diverse training data, inaccessible target data, and the large domain shift that may exist in many real-world settings. As such data augmentation is a critical component of domain generalization methods that seek to address this problem. We present Adversarial Bayesian Augmentation (ABA), a novel algorithm that learns to generate image augmentations in the challenging single-source domain generalization setting. ABA draws on the strengths of adversarial learning and Bayesian neural networks to guide the generation of diverse data augmentations –these synthesized image domains aid the classifier in generalizing to unseen domains. We demonstrate the strength of ABA on several types of domain shift including style shift, subpopulation shift, and shift in the medical imaging setting. ABA outperforms all previous state-of-the-art methods, including pre-specified augmentations, pixel-based and convolutional-based augmentations. Code: https://github.com/shengcheng/ABA.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Reducing Domain Gap by Reducing Style Bias2021
- Learning to Learn Single Domain Generalization2020
- Domain Generalization by Solving Jigsaw Puzzles2019
- Disentangling Adversarial Robustness and Generalization2019
- Domain Generalization with Domain-Specific Aggregation Modules2019
- Deep Residual Learning for Image Recognition2016
- Deep neural networks are easily fooled: High confidence predictions for unrecognizable images2015
- Semi-supervised Domain Adaptation with Subspace Learning for visual recognition2015
- ImageNet: A large-scale hierarchical image database2009
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998