Research Area:  Machine Learning

Abstract:

The generation of artificial data based on existing observations, known as data augmentation, is a technique used in machine learning to improve model accuracy, generalisation, and to control overfitting. Augmentor is a software package, available in both Python and Julia versions, that provides a high level API for the expansion of image data using a stochastic, pipeline-based approach which effectively allows for images to be sampled from a distribution of augmented images at runtime. Augmentor provides methods for most standard augmentation practices as well as several advanced features such as label-preserving, randomised elastic distortions, and provides many helper functions for typical augmentation tasks used in machine learning.

Keywords:  

Author(s) Name:  Marcus D. Bloice, Christof Stocker, Andreas Holzinger

Publisher name:  arXiv:1708.04680

DOI:  10.48550/arXiv.1708.04680

Volume Information:  Volume 2017

Paper Link:   https://arxiv.org/abs/1708.04680