Interleaved Noise Injection Improves Model Robustness on Clean, Corrupted, and OOD Data

Jul 17, 2026

A new preprint introduces interleaved noise injection—alternating between noisy and clean data phases during training—instead of the standard monotonic decay schedule. This approach, combined with a gradient-norm stabilization technique, leads to improved robustness and test performance on clean, corrupted, and out-of-distribution datasets. The method outperforms common augmentations on CIFAR-100-C, ImageNet-C, and ImageNet-R benchmarks for both ResNet and ViT architectures, and is shown to be computationally efficient.

Why it matters: This technique provides a simple and computationally efficient way to enhance model robustness to distribution shifts and data corruption, with theoretical insights into its regularization effects.

Full story at: arXiv Machine Learning ↗