Robust Classification by Coupling Data Mollification with Label Smoothing
This work addresses robustness issues in image classification for applications requiring reliable performance under corruptions, but it is incremental as it builds on existing augmentation techniques.
The paper tackles the problem of improving robustness and uncertainty quantification in deep neural networks against test-time corruptions by coupling data mollification (image noising and blurring) with label smoothing, resulting in demonstrated improvements on corrupted image benchmarks like CIFAR, TinyImageNet, and ImageNet.
Introducing training-time augmentations is a key technique to enhance generalization and prepare deep neural networks against test-time corruptions. Inspired by the success of generative diffusion models, we propose a novel approach of coupling data mollification, in the form of image noising and blurring, with label smoothing to align predicted label confidences with image degradation. The method is simple to implement, introduces negligible overheads, and can be combined with existing augmentations. We demonstrate improved robustness and uncertainty quantification on the corrupted image benchmarks of CIFAR, TinyImageNet and ImageNet datasets.