Institutions | About Us | Help | Gaeilge
rian logo


Mark
Go Back
Smart augmentation learning an optimal data augmentation strategy
Lemley, Joseph; Bazrafkan, Shabab; Corcoran, Peter
A recurring problem faced when training neural networks is that there is typically not enough data to maximize the generalization capability of deep neural networks. There are many techniques to address this, including data augmentation, dropout, and transfer learning. In this paper, we introduce an additional method, which we call smart augmentation and we show how to use it to increase the accuracy and reduce over fitting on a target network. Smart augmentation works, by creating a network that learns how to generate augmented data during the training process of a target network in a way that reduces that networks loss. This allows us to learn augmentations that minimize the error of that network. Smart augmentation has shown the potential to increase accuracy by demonstrably significant measures on all data sets tested. In addition, it has shown potential to achieve similar or improved performance levels with significantly smaller network sizes in a number of tested cases. This research is funded under the SFI Strategic Partnership Program by Science Foundation Ireland (SFI) and FotoNation Ltd. Project ID: 13/SPP/I2868 on Next Generation Imaging for Smartphone and Embedded Platforms. This work is also supported by an Irish Research Council Employment Based Programme Award. The authors gratefully acknowledge the support of NVIDIA Corporation with the donation of a Titan X GPU used for this research.
Keyword(s): Artificial intelligence; Artificial neural networks; Machine learning; Computer vision supervised learning; Machine learning algorithms; Image databases
Publication Date:
2018
Type: Journal article
Peer-Reviewed: Yes
Language(s): English
Contributor(s): NVIDIA Corporation; Science Foundation Ireland; Irish Research Council
Institution: NUI Galway
Publisher(s): Institute of Electrical and Electronics Engineers (IEEE)
File Format(s): application/pdf
First Indexed: 2019-03-23 06:45:35 Last Updated: 2019-03-23 06:45:35