# AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiation

arXiv: https://arxiv.org/abs/2103.05863 · HTML: https://mlsanity.com/paper/2103.05863/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 49 references that are in the map.
- First posted on arXiv 10 Mar 2021.

## Builds on (most cited first, 30 of 33)

- [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)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [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)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [Deep Equilibrium Models](https://mlsanity.com/paper/1909.01377/) (2019)
- [Meta-Learning with Implicit Gradients](https://mlsanity.com/paper/1909.04630/) (2019)
- [Population Based Training of Neural Networks](https://mlsanity.com/paper/1711.09846/) (2017)
- [Optimizing Millions of Hyperparameters by Implicit Differentiation](https://mlsanity.com/paper/1911.02590/) (2019)
- [Joint Optimization Framework for Learning with Noisy Labels](https://mlsanity.com/paper/1803.11364/) (2018)
- [Fast AutoAugment](https://mlsanity.com/paper/1905.00397/) (2019)
- [Hyperparameter optimization with approximate gradient](https://mlsanity.com/paper/1602.02355/) (2016)
- [Kornia: an Open Source Differentiable Computer Vision Library for PyTorch](https://mlsanity.com/paper/1910.02190/) (2019)
- [Probabilistic End-to-end Noise Correction for Learning with Noisy Labels](https://mlsanity.com/paper/1903.07788/) (2019)
- [Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules](https://mlsanity.com/paper/1905.05393/) (2019)
- [Adversarial AutoAugment](https://mlsanity.com/paper/1912.11188/) (2019)
- [Faster AutoAugment: Learning Augmentation Strategies using Backpropagation](https://mlsanity.com/paper/1911.06987/) (2019)
- [A Comprehensive Study on Face Recognition Biases Beyond Demographics](https://mlsanity.com/paper/2103.01592/) (2021)
- [Continuously Differentiable Exponential Linear Units](https://mlsanity.com/paper/1704.07483/) (2017)
- [DADA: Differentiable Automatic Data Augmentation](https://mlsanity.com/paper/2003.03780/) (2020)
- [Every Model Learned by Gradient Descent Is Approximately a Kernel Machine](https://mlsanity.com/paper/2012.00152/) (2020)
- [A Bayesian Data Augmentation Approach for Learning Deep Models](https://mlsanity.com/paper/1710.10564/) (2017)

## Built on by (most cited first, 14 of 14)

- [CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition](https://mlsanity.com/paper/2302.05499/) (2023)
- [Making Scalable Meta Learning Practical](https://mlsanity.com/paper/2310.05674/) (2023)
- [A Survey of Automated Data Augmentation Algorithms for Deep Learning-based Image Classification Tasks](https://mlsanity.com/paper/2206.06544/) (2022)
- [FedFixer: Mitigating Heterogeneous Label Noise in Federated Learning](https://mlsanity.com/paper/2403.16561/) (2024)
- [Towards Trustworthy Machine Learning in Production: An Overview of the Robustness in MLOps Approach](https://mlsanity.com/paper/2410.21346/) (2024)
- [ReSmooth: Detecting and Utilizing OOD Samples when Training with Data Augmentation](https://mlsanity.com/paper/2205.12606/) (2022)
- [Combating Noisy Labels in Long-Tailed Image Classification](https://mlsanity.com/paper/2209.00273/) (2022)
- [Hyperbolic Dual Feature Augmentation for Open-Environment](https://mlsanity.com/paper/2506.08906/) (2025)
- [DualAug: Exploiting Additional Heavy Augmentation with OOD Data Rejection](https://mlsanity.com/paper/2310.08139/) (2023)
- [Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods](https://mlsanity.com/paper/2403.08352/) (2024)
- [Fisher-aware Quantization for DETR Detectors with Critical-category Objectives](https://mlsanity.com/paper/2407.03442/) (2024)
- [Efficient Scheduling of Data Augmentation for Deep Reinforcement Learning](https://mlsanity.com/paper/2206.00518/) (2022)
- [A Study of Deep CNN Model with Labeling Noise Based on Granular-ball Computing](https://mlsanity.com/paper/2207.08810/) (2022)
- [Variational Rectification Inference for Learning with Noisy Labels](https://mlsanity.com/paper/2603.17255/) (2026)

## Abstract (arXiv)

AutoAugment has sparked an interest in automated augmentation methods for deep learning models. These methods estimate image transformation policies for train data that improve generalization to test data. While recent papers evolved in the direction of decreasing policy search complexity, we show that those methods are not robust when applied to biased and noisy data. To overcome these limitations, we reformulate AutoAugment as a generalized automated dataset optimization (AutoDO) task that minimizes the distribution shift between test data and distorted train dataset. In our AutoDO model, we explicitly estimate a set of per-point hyperparameters to flexibly change distribution of train data. In particular, we include hyperparameters for augmentation, loss weights, and soft-labels that are jointly estimated using implicit differentiation. We develop a theoretical probabilistic interpretation of this framework using Fisher information and show that its complexity scales linearly with the dataset size. Our experiments on SVHN, CIFAR-10/100, and ImageNet classification show up to 9.3% improvement for biased datasets with label noise compared to prior methods and, importantly, up to 36.6% gain for underrepresented SVHN classes.