# Combined Image Data Augmentations diminish the benefits of Adaptive Label Smoothing

arXiv: https://arxiv.org/abs/2507.16427 · HTML: https://mlsanity.com/paper/2507.16427/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 41 references that are in the map.
- First posted on arXiv 22 Jul 2025.

## Builds on (most cited first, 21 of 21)

- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation](https://mlsanity.com/paper/2103.10158/) (2021)
- [Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation](https://mlsanity.com/paper/1906.02611/) (2019)
- [Delving Deep into Label Smoothing](https://mlsanity.com/paper/2011.12562/) (2020)
- [Label Refinery: Improving ImageNet Classification through Label Progression](https://mlsanity.com/paper/1805.02641/) (2018)
- [DisturbLabel: Regularizing CNN on the Loss Layer](https://mlsanity.com/paper/1605.00055/) (2016)
- [Learning Soft Labels via Meta Learning](https://mlsanity.com/paper/2009.09496/) (2020)
- [Recurrent computations for visual pattern completion](https://mlsanity.com/paper/1706.02240/) (2017)
- [Robustness of Object Recognition under Extreme Occlusion in Humans and Computational Models](https://mlsanity.com/paper/1905.04598/) (2019)
- [NoisyMix: Boosting Model Robustness to Common Corruptions](https://mlsanity.com/paper/2202.01263/) (2022)
- [Soft Augmentation for Image Classification](https://mlsanity.com/paper/2211.04625/) (2022)
- [Investigating the Corruption Robustness of Image Classifiers with Random Lp-norm Corruptions](https://mlsanity.com/paper/2305.05400/) (2023)

## Abstract (arXiv)

Soft augmentation regularizes the supervised learning process of image classifiers by reducing label confidence of a training sample based on the magnitude of random-crop augmentation applied to it. This paper extends this adaptive label smoothing framework to other types of aggressive augmentations beyond random-crop. Specifically, we demonstrate the effectiveness of the method for random erasing and noise injection data augmentation. Adaptive label smoothing permits stronger regularization via higher-intensity Random Erasing. However, its benefits vanish when applied with a diverse range of image transformations as in the state-of-the-art TrivialAugment method, and excessive label smoothing harms robustness to common corruptions. Our findings suggest that adaptive label smoothing should only be applied when the training data distribution is dominated by a limited, homogeneous set of image transformation types.