Robust Classification by Coupling Data Mollification with Label Smoothing
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 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.
Cite
Text
Heinonen et al. "Robust Classification by Coupling Data Mollification with Label Smoothing." Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, 2025.Markdown
[Heinonen et al. "Robust Classification by Coupling Data Mollification with Label Smoothing." Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, 2025.](https://mlanthology.org/aistats/2025/heinonen2025aistats-robust/)BibTeX
@inproceedings{heinonen2025aistats-robust,
title = {{Robust Classification by Coupling Data Mollification with Label Smoothing}},
author = {Heinonen, Markus and Tran, Ba-Hien and Kampffmeyer, Michael and Filippone, Maurizio},
booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics},
year = {2025},
pages = {4960-4968},
volume = {258},
url = {https://mlanthology.org/aistats/2025/heinonen2025aistats-robust/}
}