Image Augmentation using Radial Transform for Training Deep Neural Networks

TL;DR

This paper introduces a novel image augmentation technique using radial transform in polar coordinates to enhance deep neural network training, especially with limited or imbalanced data, leading to improved generalization.

Contribution

It presents a new pixel-wise radial transform method for image augmentation that increases data diversity and improves deep learning model performance.

Findings

Enhanced generalization in CNNs trained with radial transformed images

Increased diversity of training data for poorly represented classes

Improved accuracy on limited or imbalanced datasets

Abstract

Deep learning models have a large number of free parameters that must be estimated by efficient training of the models on a large number of training data samples to increase their generalization performance. In real-world applications, the data available to train these networks is often limited or imbalanced. We propose a sampling method based on the radial transform in a polar coordinate system for image augmentation to facilitate the training of deep learning models from limited source data. This pixel-wise transform provides representations of the original image in the polar coordinate system by generating a new image from each pixel. This technique can generate radial transformed images up to the number of pixels in the original image to increase the diversity of poorly represented image classes. Our experiments show improved generalization performance in training deep convolutional neural networks with radial transformed images.