1. Robust Classification by Coupling Data Mollification with Label Smoothing
- Author
-
Heinonen, Markus, Tran, Ba-Hien, Kampffmeyer, Michael, and Filippone, Maurizio
- Subjects
Computer Science - Computer Vision and Pattern Recognition ,Computer Science - Machine Learning ,Statistics - Machine Learning - Abstract
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 coupling data augmentation, 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 the CIFAR and TinyImageNet datasets., Comment: Under review
- Published
- 2024