# Learning to Compose Domain-Specific Transformations for Data Augmentation

arXiv: https://arxiv.org/abs/1709.01643 · HTML: https://mlsanity.com/paper/1709.01643/

## Key facts

- Cited by 91 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Sep 2017.

## Built on by (most cited first, 30 of 91)

- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [A Survey of Data Augmentation Approaches for NLP](https://mlsanity.com/paper/2105.03075/) (2021)
- [Dataset Condensation with Differentiable Siamese Augmentation](https://mlsanity.com/paper/2102.08259/) (2021)
- [SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption](https://mlsanity.com/paper/2106.15147/) (2021)
- [Deep Stable Learning for Out-Of-Distribution Generalization](https://mlsanity.com/paper/2104.07876/) (2021)
- [Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective](https://mlsanity.com/paper/2112.06409/) (2021)
- [A Survey on Data Augmentation for Text Classification](https://mlsanity.com/paper/2107.03158/) (2021)
- [MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2103.12579/) (2021)
- [Neural Transformation Learning for Deep Anomaly Detection Beyond Images](https://mlsanity.com/paper/2103.16440/) (2021)
- [A Comprehensive Survey of Image Augmentation Techniques for Deep Learning](https://mlsanity.com/paper/2205.01491/) (2022)
- [Ensembling with Deep Generative Views](https://mlsanity.com/paper/2104.14551/) (2021)
- [Hybrid Relation Guided Set Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2204.13423/) (2022)
- [Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classification](https://mlsanity.com/paper/2111.06399/) (2021)
- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [Test time Adaptation through Perturbation Robustness](https://mlsanity.com/paper/2110.10232/) (2021)
- [Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification](https://mlsanity.com/paper/2112.07928/) (2021)
- [The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective](https://mlsanity.com/paper/2210.05021/) (2022)
- [Scale-aware Automatic Augmentation for Object Detection](https://mlsanity.com/paper/2103.17220/) (2021)
- [Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments](https://mlsanity.com/paper/2105.08149/) (2021)
- [Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models](https://mlsanity.com/paper/2103.00429/) (2021)
- [How to Train Your MAML to Excel in Few-Shot Classification](https://mlsanity.com/paper/2106.16245/) (2021)
- [Mitigating Data Heterogeneity in Federated Learning with Data Augmentation](https://mlsanity.com/paper/2206.09979/) (2022)
- [Automated Data Augmentations for Graph Classification](https://mlsanity.com/paper/2202.13248/) (2022)
- [Out-of-Domain Generalization from a Single Source: An Uncertainty Quantification Approach](https://mlsanity.com/paper/2108.02888/) (2021)
- [AADG: Automatic Augmentation for Domain Generalization on Retinal Image Segmentation](https://mlsanity.com/paper/2207.13249/) (2022)
- [Learning Multimodal Data Augmentation in Feature Space](https://mlsanity.com/paper/2212.14453/) (2022)
- [LARGE: Latent-Based Regression through GAN Semantics](https://mlsanity.com/paper/2107.11186/) (2021)
- [Data Augmentation vs. Equivariant Networks: A Theory of Generalization on Dynamics Forecasting](https://mlsanity.com/paper/2206.09450/) (2022)
- [Improving Diversity with Adversarially Learned Transformations for Domain Generalization](https://mlsanity.com/paper/2206.07736/) (2022)
- [Learning Augmentation Distributions using Transformed Risk Minimization](https://mlsanity.com/paper/2111.08190/) (2021)

## Abstract (arXiv)

Data augmentation is a ubiquitous technique for increasing the size of labeled training sets by leveraging task-specific data transformations that preserve class labels. While it is often easy for domain experts to specify individual transformations, constructing and tuning the more sophisticated compositions typically needed to achieve state-of-the-art results is a time-consuming manual task in practice. We propose a method for automating this process by learning a generative sequence model over user-specified transformation functions using a generative adversarial approach. Our method can make use of arbitrary, non-deterministic transformation functions, is robust to misspecified user input, and is trained on unlabeled data. The learned transformation model can then be used to perform data augmentation for any end discriminative model. In our experiments, we show the efficacy of our approach on both image and text datasets, achieving improvements of 4.0 accuracy points on CIFAR-10, 1.4 F1 points on the ACE relation extraction task, and 3.4 accuracy points when using domain-specific transformation operations on a medical imaging dataset as compared to standard heuristic augmentation approaches.