English

Towards Combating Frequency Simplicity-biased Learning for Domain Generalization

Machine Learning 2024-10-22 v1 Computer Vision and Pattern Recognition

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. Code is available at AdvFrequency (https://github.com/C0notSilly/AdvFrequency).

Keywords

Cite

@article{arxiv.2410.16146,
  title  = {Towards Combating Frequency Simplicity-biased Learning for Domain Generalization},
  author = {Xilin He and Jingyu Hu and Qinliang Lin and Cheng Luo and Weicheng Xie and Siyang Song and Muhammad Haris Khan and Linlin Shen},
  journal= {arXiv preprint arXiv:2410.16146},
  year   = {2024}
}

Comments

Accepted by NeurIPS 2024

R2 v1 2026-06-28T19:29:58.109Z