Understanding Domain Generalization: A Noise Robustness Perspective
Despite the rapid development of machine learning algorithms for domain generalization (DG), there is no clear empirical evidence that the existing DG algorithms outperform the classic empirical risk minimization (ERM) across standard benchmarks. To better understand this phenomenon, we investigate whether there are benefits of DG algorithms over ERM through the lens of label noise. Specifically, our finite-sample analysis reveals that label noise exacerbates the effect of spurious correlations for ERM, undermining generalization. Conversely, we illustrate that DG algorithms exhibit implicit label-noise robustness during finite-sample training even when spurious correlation is present. Such desirable property helps mitigate spurious correlations and improve generalization in synthetic experiments. However, additional comprehensive experiments on real-world benchmark datasets indicate that label-noise robustness does not necessarily translate to better performance compared to ERM. We conjecture that the failure mode of ERM arising from spurious correlations may be less pronounced in practice.
Code (1)
Tasks
Domain GeneralizationSimilar Papers 제목 키워드 기반
Towards Adversarial Robustness of Deep Vision Algorithms
Deep learning methods have achieved great success in solving computer vision tasks, and they have been widely utilized in artificially intelligent systems for image processing, analysis, and understanding. However, deep …
Adversarial Robustnessimage-classificationImage ClassificationA Flat Minima Perspective on Understanding Augmentations and Model Robustness
Model robustness indicates a model's capability to generalize well on unforeseen distributional shifts, including data corruption, adversarial attacks, and domain shifts. Data augmentation is one of the prevalent and eff…
Adversarial RobustnessData AugmentationDomain GeneralizationSee Through the Noise: Improving Domain Generalization in Gaze Estimation
Generalizable gaze estimation methods have garnered increasing attention due to their critical importance in real-world applications and have achieved significant progress. However, they often overlook the effect of labe…
Domain GeneralizationGaze EstimationAdversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularization
Machine learning (ML) robustness and domain generalization are fundamentally correlated: they essentially concern data distribution shifts under adversarial and natural settings, respectively. On one hand, recent studies…
Domain GeneralizationNoise-Aware Generalization: Robustness to In-Domain Noise and Out-of-Domain Generalization
Multi-source Domain Generalization (DG) aims to improve model robustness to new distributions. However, DG methods often overlook the effect of label noise, which can confuse a model during training, reducing performance…
Domain GeneralizationLearning with noisy labels