# MetaAugment: Sample-Aware Data Augmentation Policy Learning

arXiv: https://arxiv.org/abs/2012.12076 · HTML: https://mlsanity.com/paper/2012.12076/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2020.

## Built on by (most cited first, 19 of 19)

- [Direct Differentiable Augmentation Search](https://mlsanity.com/paper/2104.04282/) (2021)
- [Automatic Data Augmentation via Invariance-Constrained Learning](https://mlsanity.com/paper/2209.15031/) (2022)
- [Learning Instance-Specific Augmentations by Capturing Local Invariances](https://mlsanity.com/paper/2206.00051/) (2022)
- [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)
- [Understanding the Detrimental Class-level Effects of Data Augmentation](https://mlsanity.com/paper/2401.01764/) (2023)
- [DHA: End-to-End Joint Optimization of Data Augmentation Policy, Hyper-parameter and Architecture](https://mlsanity.com/paper/2109.05765/) (2021)
- [Data Optimization in Deep Learning: A Survey](https://mlsanity.com/paper/2310.16499/) (2023)
- [Sample-aware RandAugment: Search-free Automatic Data Augmentation for Effective Image Recognition](https://mlsanity.com/paper/2508.08004/) (2025)
- [Synth4Seg -- Learning Defect Data Synthesis for Defect Segmentation using Bi-level Optimization](https://mlsanity.com/paper/2410.18490/) (2024)
- [LatentAugment: Dynamically Optimized Latent Probabilities of Data Augmentation](https://mlsanity.com/paper/2305.02668/) (2023)
- [Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods](https://mlsanity.com/paper/2403.08352/) (2024)
- [Variational Partial Group Convolutions for Input-Aware Partial Equivariance of Rotations and Color-Shifts](https://mlsanity.com/paper/2407.04271/) (2024)
- [GREAT: Generalizable Representation Enhancement via Auxiliary Transformations for Zero-Shot Environmental Prediction](https://mlsanity.com/paper/2511.13469/) (2025)
- [LA3: Efficient Label-Aware AutoAugment](https://mlsanity.com/paper/2304.10310/) (2023)
- [Reducing and Exploiting Data Augmentation Noise through Meta Reweighting Contrastive Learning for Text Classification](https://mlsanity.com/paper/2409.17474/) (2024)
- [AutoGeTS: Knowledge-based Automated Generation of Text Synthetics for Improving Text Classification](https://mlsanity.com/paper/2508.10000/) (2025)
- [Ctrl-A: Control-Driven Online Data Augmentation](https://mlsanity.com/paper/2603.21819/) (2026)

## Abstract (arXiv)

Automated data augmentation has shown superior performance in image recognition. Existing works search for dataset-level augmentation policies without considering individual sample variations, which are likely to be sub-optimal. On the other hand, learning different policies for different samples naively could greatly increase the computing cost. In this paper, we learn a sample-aware data augmentation policy efficiently by formulating it as a sample reweighting problem. Specifically, an augmentation policy network takes a transformation and the corresponding augmented image as inputs, and outputs a weight to adjust the augmented image loss computed by a task network. At training stage, the task network minimizes the weighted losses of augmented training images, while the policy network minimizes the loss of the task network on a validation set via meta-learning. We theoretically prove the convergence of the training procedure and further derive the exact convergence rate. Superior performance is achieved on widely-used benchmarks including CIFAR-10/100, Omniglot, and ImageNet.