Go to ICLR 2026 Conference homepageDRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation
Keywords: Distributionally Robust Optimization；Data Augmentation；Deep Learning；Multi-class Classification
TL;DR: We propose DRO-Augment, a framework combining W-DRO and data augmentation, with both strong empirical robustness and theoretical generalization guarantees. We also proposed refined CIFAR-C datasets
Abstract: In many real-world applications, ensuring the robustness and stability of deep neural networks (DNNs) is crucial, particularly for image classification tasks that encounter various input perturbations. While data augmentation techniques have been widely adopted to enhance the resilience of a trained model against such perturbations, there remains significant room for improvement in robustness against corrupted data and adversarial attacks simultaneously.
To address this challenge, we introduce DRO-Augment, a novel framework that integrates Wasserstein Distributionally Robust Optimization (W-DRO) with various data augmentation strategies to improve the robustness of the models significantly across a broad spectrum of corruptions.
Our method outperforms existing augmentation methods under severe data perturbations and adversarial attack scenarios while maintaining the accuracy on the clean datasets on a range of benchmark datasets, including but not limited to CIFAR-10-C, CIFAR-100-C, Tiny-ImageNet-C, and Fashion-MNIST.
On the theoretical side, we establish novel generalization error bounds for neural networks trained using a computationally efficient, variation-regularized loss function with augmented data, closely related to the W-DRO problem. Furthermore, we introduce a refined CIFAR-C benchmark that corrects inconsistencies in corruption intensities, providing a more reliable evaluation for future robustness research.
Primary Area: applications to computer vision, audio, language, and other modalities
Submission Number: 8096
Loading