Effective real-time augmentation of training dataset for the neural networks learning

Alexander V. Gayer; Yulia S. Chernyshova; Alexander V. Sheshkus

doi:10.1117/12.2522969

15 March 2019 Effective real-time augmentation of training dataset for the neural networks learning

Alexander V. Gayer, Yulia S. Chernyshova, Alexander V. Sheshkus

Proceedings Volume 11041, Eleventh International Conference on Machine Vision (ICMV 2018); 110411I (2019) https://doi.org/10.1117/12.2522969
Event: Eleventh International Conference on Machine Vision (ICMV 2018), 2018, Munich, Germany

Abstract

In this paper we study the real-time augmentation - method of increasing variability of training dataset during the learning process. We consider the most common label-preserving deformations, which can be useful in many practical tasks. Due to limitations of existing augmentation tools like increase in learning time or dependence on a specific platform, we developed own real-time augmentation system. Experiments on MNIST and SVHN datasets demonstrated the effectiveness of suggested approach - the quality of the trained models improves, and learning time remains the same as if augmentation was not used.

Citation Download Citation

Alexander V. Gayer, Yulia S. Chernyshova, and Alexander V. Sheshkus "Effective real-time augmentation of training dataset for the neural networks learning", Proc. SPIE 11041, Eleventh International Conference on Machine Vision (ICMV 2018), 110411I (15 March 2019); https://doi.org/10.1117/12.2522969

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available