Proceedings Paper
Effective real-time augmentation of training dataset for the neural networks learning| Format | Member Price | Non-Member Price |
|---|---|---|
| $17.00 | $21.00 |
Paper 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.
Paper Details
Date Published: 15 March 2019
PDF: 8 pages
Proc. SPIE 11041, Eleventh International Conference on Machine Vision (ICMV 2018), 110411I (15 March 2019); doi: 10.1117/12.2522969
Published in SPIE Proceedings Vol. 11041:
Eleventh International Conference on Machine Vision (ICMV 2018)
Antanas Verikas; Dmitry P. Nikolaev; Petia Radeva; Jianhong Zhou, Editor(s)
PDF: 8 pages
Proc. SPIE 11041, Eleventh International Conference on Machine Vision (ICMV 2018), 110411I (15 March 2019); doi: 10.1117/12.2522969
Show Author Affiliations
Alexander V. Gayer, National Univ. of Science and Technology MISIS (Russian Federation)
Smart Engines Ltd. (Russian Federation)
Yulia S. Chernyshova, Smart Engines Ltd. (Russian Federation)
Institute for Systems Analysis (Russian Federation)
Smart Engines Ltd. (Russian Federation)
Yulia S. Chernyshova, Smart Engines Ltd. (Russian Federation)
Institute for Systems Analysis (Russian Federation)
Alexander V. Sheshkus, Smart Engines Ltd. (Russian Federation)
Published in SPIE Proceedings Vol. 11041:
Eleventh International Conference on Machine Vision (ICMV 2018)
Antanas Verikas; Dmitry P. Nikolaev; Petia Radeva; Jianhong Zhou, Editor(s)
© SPIE. Terms of Use
