# Further advantages of data augmentation on convolutional neural networks

arXiv: https://arxiv.org/abs/1906.11052 · HTML: https://mlsanity.com/paper/1906.11052/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2019.

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

- [Taken out of context: On measuring situational awareness in LLMs](https://mlsanity.com/paper/2309.00667/) (2023)
- [Randomness In Neural Network Training: Characterizing The Impact of Tooling](https://mlsanity.com/paper/2106.11872/) (2021)
- [How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization](https://mlsanity.com/paper/2210.06441/) (2022)
- [Domain Generalization via Inference-time Label-Preserving Target Projections](https://mlsanity.com/paper/2103.01134/) (2021)
- [Data Augmentation vs. Equivariant Networks: A Theory of Generalization on Dynamics Forecasting](https://mlsanity.com/paper/2206.09450/) (2022)
- [A Data-Augmentation Is Worth A Thousand Samples: Exact Quantification From Analytical Augmented Sample Moments](https://mlsanity.com/paper/2202.08325/) (2022)
- [Understanding the Detrimental Class-level Effects of Data Augmentation](https://mlsanity.com/paper/2401.01764/) (2023)
- [FAIR-Ensemble: When Fairness Naturally Emerges From Deep Ensembling](https://mlsanity.com/paper/2303.00586/) (2023)
- [Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularization](https://mlsanity.com/paper/2202.01832/) (2022)
- [EllSeg-Gen, towards Domain Generalization for head-mounted eyetracking](https://mlsanity.com/paper/2205.01947/) (2022)
- [Steerable Equivariant Representation Learning](https://mlsanity.com/paper/2302.11349/) (2023)
- [A Probabilistic Framework for Knowledge Graph Data Augmentation](https://mlsanity.com/paper/2110.13205/) (2021)
- [Multi-Sample zeta-mixup: Richer, More Realistic Synthetic Samples from a p-Series Interpolant](https://mlsanity.com/paper/2204.03323/) (2022)
- [An Embarrassingly Pragmatic Introduction to Vision-based Autonomous Robots](https://mlsanity.com/paper/2112.05534/) (2021)
- [A Computer Vision-Based Quality Assessment Technique for the automatic control of consumables for analytical laboratories](https://mlsanity.com/paper/2404.10454/) (2024)
- [Image Recognition for Garbage Classification Based on Pixel Distribution Learning](https://mlsanity.com/paper/2409.03913/) (2024)
- [Pseudo-Nonlinear Data Augmentation: A Constrained Energy Minimization Viewpoint](https://mlsanity.com/paper/2410.00718/) (2024)
- [Regularizing Attention Scores with Bootstrapping](https://mlsanity.com/paper/2604.01339/) (2026)
- [Towards Sustainable Artificial Intelligence: A Comprehensive Review and Comparative Analysis of Deep Learning Models' Carbon Footprint](https://mlsanity.com/paper/2608.09998/) (2026)

## Abstract (arXiv)

Data augmentation is a popular technique largely used to enhance the training of convolutional neural networks. Although many of its benefits are well known by deep learning researchers and practitioners, its implicit regularization effects, as compared to popular explicit regularization techniques, such as weight decay and dropout, remain largely unstudied. As a matter of fact, convolutional neural networks for image object classification are typically trained with both data augmentation and explicit regularization, assuming the benefits of all techniques are complementary. In this paper, we systematically analyze these techniques through ablation studies of different network architectures trained with different amounts of training data. Our results unveil a largely ignored advantage of data augmentation: networks trained with just data augmentation more easily adapt to different architectures and amount of training data, as opposed to weight decay and dropout, which require specific fine-tuning of their hyperparameters.