# Improved Mixed-Example Data Augmentation

arXiv: https://arxiv.org/abs/1805.11272 · HTML: https://mlsanity.com/paper/1805.11272/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2018.

## Built on by (most cited first, 30 of 42)

- [SynFace: Face Recognition with Synthetic Data](https://mlsanity.com/paper/2108.07960/) (2021)
- [The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification](https://mlsanity.com/paper/2112.00412/) (2021)
- [3D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detection](https://mlsanity.com/paper/2112.04764/) (2021)
- [AlignMixup: Improving Representations By Interpolating Aligned Features](https://mlsanity.com/paper/2103.15375/) (2021)
- [MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks](https://mlsanity.com/paper/2103.06132/) (2021)
- [A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability](https://mlsanity.com/paper/2212.10888/) (2022)
- [Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognition](https://mlsanity.com/paper/2112.04178/) (2021)
- [Survey: Image Mixing and Deleting for Data Augmentation](https://mlsanity.com/paper/2106.07085/) (2021)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [A Survey on Mixup Augmentations and Beyond](https://mlsanity.com/paper/2409.05202/) (2024)
- [Fine-grained Recognition with Learnable Semantic Data Augmentation](https://mlsanity.com/paper/2309.00399/) (2023)
- [An overview of mixing augmentation methods and augmentation strategies](https://mlsanity.com/paper/2107.09887/) (2021)
- [IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers](https://mlsanity.com/paper/2310.04780/) (2023)
- [Learning from Neighbors: Category Extrapolation for Long-Tail Learning](https://mlsanity.com/paper/2410.15980/) (2024)
- [Physical Knowledge Enhanced Deep Neural Network for Sea Surface Temperature Prediction](https://mlsanity.com/paper/2304.09376/) (2023)
- [Data Augmentation for Graph Convolutional Network on Semi-Supervised Classification](https://mlsanity.com/paper/2106.08848/) (2021)
- [Contrastive-mixup learning for improved speaker verification](https://mlsanity.com/paper/2202.10672/) (2022)
- [Principled Ultrasound Data Augmentation for Classification of Standard Planes](https://mlsanity.com/paper/2103.07895/) (2021)
- [Tailoring Mixup to Data for Calibration](https://mlsanity.com/paper/2311.01434/) (2023)
- [3D Adversarial Augmentations for Robust Out-of-Domain Predictions](https://mlsanity.com/paper/2308.15479/) (2023)
- [MSE Loss with Outlying Label for Imbalanced Classification](https://mlsanity.com/paper/2107.02393/) (2021)
- [Feature transforms for image data augmentation](https://mlsanity.com/paper/2201.09700/) (2022)
- [Global Mixup: Eliminating Ambiguity with Clustering](https://mlsanity.com/paper/2206.02734/) (2022)
- [Data augmentation by morphological mixup for solving Raven's Progressive Matrices](https://mlsanity.com/paper/2103.05222/) (2021)
- [Similarity Transfer for Knowledge Distillation](https://mlsanity.com/paper/2103.10047/) (2021)
- [On the Effects of Artificial Data Modification](https://mlsanity.com/paper/2110.13968/) (2021)
- [Light In The Black: An Evaluation of Data Augmentation Techniques for COVID-19 CT's Semantic Segmentation](https://mlsanity.com/paper/2205.09722/) (2022)
- [Extending Temporal Data Augmentation for Video Action Recognition](https://mlsanity.com/paper/2211.04888/) (2022)
- [Epsilon Consistent Mixup: Structural Regularization with an Adaptive Consistency-Interpolation Tradeoff](https://mlsanity.com/paper/2104.09452/) (2021)
- [Fine-Grained AutoAugmentation for Multi-Label Classification](https://mlsanity.com/paper/2107.05384/) (2021)

## Abstract (arXiv)

In order to reduce overfitting, neural networks are typically trained with data augmentation, the practice of artificially generating additional training data via label-preserving transformations of existing training examples. While these types of transformations make intuitive sense, recent work has demonstrated that even non-label-preserving data augmentation can be surprisingly effective, examining this type of data augmentation through linear combinations of pairs of examples. Despite their effectiveness, little is known about why such methods work. In this work, we aim to explore a new, more generalized form of this type of data augmentation in order to determine whether such linearity is necessary. By considering this broader scope of "mixed-example data augmentation", we find a much larger space of practical augmentation techniques, including methods that improve upon previous state-of-the-art. This generalization has benefits beyond the promise of improved performance, revealing a number of types of mixed-example data augmentation that are radically different from those considered in prior work, which provides evidence that current theories for the effectiveness of such methods are incomplete and suggests that any such theory must explain a much broader phenomenon. Code is available at https://github.com/ceciliaresearch/MixedExample.