# Meta Approach to Data Augmentation Optimization

Source: [Meta Approach to Data Augmentation Optimization](<https://www.sota2.com/research/paper/68fa67b31e209131cea17e70>)

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

Data updated: 2025-10-25T22:20:05.971Z

Authors: Ryuichiro Hataya, Jan Zdenek, Kazuki Yoshizoe, Hideki Nakayama

Published: 2020-06-14T18:11:52.000Z

## Abstract

Data augmentation policies drastically improve the performance of image recognition tasks, especially when the policies are optimized for the target data and tasks. In this paper, we propose to optimize image recognition models and data augmentation policies simultaneously to improve the performance using gradient descent. Unlike prior methods, our approach avoids using proxy tasks or reducing search space, and can directly improve the validation performance. Our method achieves efficient and scalable training by approximating the gradient of policies by implicit gradient with Neumann series approximation. We demonstrate that our approach can improve the performance of various image classification tasks, including ImageNet classification and fine-grained recognition, without using dataset-specific hyperparameter tuning.

## 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/2006.07965>)

[PDF](<https://arxiv.org/pdf/2006.07965.pdf>)