# Robust Classification by Coupling Data Mollification with Label Smoothing

Source: [Robust Classification by Coupling Data Mollification with Label Smoothing](<https://www.sota2.com/research/paper/68fa78541e209131cea77bbd>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:36:17.760Z

Authors: Markus Heinonen, Ba-Hien Tran, Michael Kampffmeyer, Maurizio Filippone

Published: 2024-06-03T16:21:29.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2406.01494>)

[PDF](<https://arxiv.org/pdf/2406.01494.pdf>)