# Learning Data Augmentation with Online Bilevel Optimization for Image Classification

arXiv: https://arxiv.org/abs/2006.14699 · HTML: https://mlsanity.com/paper/2006.14699/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jun 2020.

## Built on by (most cited first, 20 of 20)

- [Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond](https://mlsanity.com/paper/2101.11517/) (2021)
- [On Implicit Bias in Overparameterized Bilevel Optimization](https://mlsanity.com/paper/2212.14032/) (2022)
- [Direct Differentiable Augmentation Search](https://mlsanity.com/paper/2104.04282/) (2021)
- [An overview of mixing augmentation methods and augmentation strategies](https://mlsanity.com/paper/2107.09887/) (2021)
- [Automated data processing and feature engineering for deep learning and big data applications: a survey](https://mlsanity.com/paper/2403.11395/) (2024)
- [When to Learn What: Model-Adaptive Data Augmentation Curriculum](https://mlsanity.com/paper/2309.04747/) (2023)
- [A Survey of the Self Supervised Learning Mechanisms for Vision Transformers](https://mlsanity.com/paper/2408.17059/) (2024)
- [Story Visualization by Online Text Augmentation with Context Memory](https://mlsanity.com/paper/2308.07575/) (2023)
- [Deep Image Harmonization with Learnable Augmentation](https://mlsanity.com/paper/2308.00376/) (2023)
- [Domain Generalization by Rejecting Extreme Augmentations](https://mlsanity.com/paper/2310.06670/) (2023)
- [FreeAugment: Data Augmentation Search Across All Degrees of Freedom](https://mlsanity.com/paper/2409.04820/) (2024)
- [Online Nonconvex Bilevel Optimization with Bregman Divergences](https://mlsanity.com/paper/2409.10470/) (2024)
- [On Automatic Data Augmentation for 3D Point Cloud Classification](https://mlsanity.com/paper/2112.06029/) (2021)
- [Automatic Data Augmentation Learning using Bilevel Optimization for Histopathological Images](https://mlsanity.com/paper/2307.11808/) (2023)
- [Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods](https://mlsanity.com/paper/2403.08352/) (2024)
- [Optimizing Data Augmentation through Bayesian Model Selection](https://mlsanity.com/paper/2505.21813/) (2025)
- [Natural Hypergradient Descent: Algorithm Design, Convergence Analysis, and Parallel Implementation](https://mlsanity.com/paper/2602.10905/) (2026)
- [GABO: Graph Augmentations with Bi-level Optimization](https://mlsanity.com/paper/2104.00722/) (2021)
- [SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation](https://mlsanity.com/paper/2410.02512/) (2024)
- [Advancing Utility Pole and Sign Detection Through Deep Learning](https://mlsanity.com/paper/2608.04061/) (2026)

## Abstract (arXiv)

Data augmentation is a key practice in machine learning for improving generalization performance. However, finding the best data augmentation hyperparameters requires domain knowledge or a computationally demanding search. We address this issue by proposing an efficient approach to automatically train a network that learns an effective distribution of transformations to improve its generalization. Using bilevel optimization, we directly optimize the data augmentation parameters using a validation set. This framework can be used as a general solution to learn the optimal data augmentation jointly with an end task model like a classifier. Results show that our joint training method produces an image classification accuracy that is comparable to or better than carefully hand-crafted data augmentation. Yet, it does not need an expensive external validation loop on the data augmentation hyperparameters.