Towards Combating Frequency Simplicity-biased Learning for Domain Generalization
He, Xilin Hu, Jingyu Lin, Qinliang Luo, Cheng Xie, Weicheng Song, Siyang Khan, Muhammad Haris Shen, Linlin
He, Xilin
Hu, Jingyu
Lin, Qinliang
Luo, Cheng
Xie, Weicheng
Song, Siyang
Khan, Muhammad Haris
Shen, Linlin
Supervisor
Department
Computer Vision
Embargo End Date
Type
Conference proceeding
Date
2024
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Domain generalization methods aim to learn transferable knowledge from source domains that can generalize well to unseen target domains. Recent studies show that neural networks frequently suffer from a simplicity-biased learning behavior which leads to over-reliance on specific frequency sets, namely as frequency shortcuts, instead of semantic information, resulting in poor generalization performance. Despite previous data augmentation techniques successfully enhancing generalization performances, they intend to apply more frequency shortcuts, thereby causing hallucinations of generalization improvement.In this paper, we aim to prevent such learning behavior of applying frequency shortcuts from a data-driven perspective. Given the theoretical justification of models' biased learning behavior on different spatial frequency components, which is based on the dataset frequency properties, we argue that the learning behavior on various frequency components could be manipulated by changing the dataset statistical structure in the Fourier domain. Intuitively, as frequency shortcuts are hidden in the dominant and highly dependent frequencies of dataset structure, dynamically perturbating the over-reliance frequency components could prevent the application of frequency shortcuts.To this end, we propose two effective data augmentation modules designed to collaboratively and adaptively adjust the frequency characteristic of the dataset, aiming to dynamically influence the learning behavior of the model and ultimately serving as a strategy to mitigate shortcut learning. Our code will be made publicly available.
Citation
X. He et al., “Towards Combating Frequency Simplicity-biased Learning for Domain Generalization,” Adv Neural Inf Process Syst, vol. 37, pp. 31078–31102, Dec. 2024.
Source
Advances in Neural Information Processing Systems (NeurIPS 2024)
Conference
Keywords
Frequency simplicity bias, Single-source domain generalization, Frequency domain learning, Domain generalization, Deep learning?
Subjects
Source
Publisher
NEURIPS