TY - GEN
T1 - Adversarial Bayesian Augmentation for Single-Source Domain Generalization
AU - Cheng, Sheng
AU - Gokhale, Tejas
AU - Yang, Yezhou
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85185870210&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85185870210&partnerID=8YFLogxK
U2 - 10.1109/ICCV51070.2023.01047
DO - 10.1109/ICCV51070.2023.01047
M3 - Conference contribution
AN - SCOPUS:85185870210
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 11366
EP - 11376
BT - Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
Y2 - 2 October 2023 through 6 October 2023
ER -