# Further advantages of data augmentation on convolutional neural networks

## TL;DR

This paper systematically analyzes the regularization effects of data augmentation in CNNs, revealing its unique advantage in enabling models to adapt to various architectures and data sizes without extensive hyperparameter tuning.

## Contribution

It provides a comprehensive study comparing data augmentation with explicit regularization techniques, highlighting its implicit regularization benefits and adaptability.

## Key findings

- Data augmentation acts as an implicit regularizer.
- Networks trained with data augmentation adapt better to different architectures.
- Data augmentation requires less hyperparameter tuning than weight decay or dropout.

## Abstract

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.