Translator Disclaimer
9 September 2019 Compactly supported frame wavelets and applications in convolutional neural networks
Author Affiliations +
Abstract
In this paper, we use the ideas presented in [1] to construct application-targeted convolutional neural network architectures (CNN). Specifically, we design frame filter banks consisting of sparse kernels with custom-selected orientations that can act as finite-difference operators. We then use these filter banks as the building blocks of structured receptive field CNNs [2] to compare baseline models with more application-oriented methods. Our tests are done on Google's Quick, Draw! data set.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Nikolaos Karantzas, Kazem Safari, Mozahid Haque, Saeed Sarmadi, and Manos Papadakis "Compactly supported frame wavelets and applications in convolutional neural networks", Proc. SPIE 11138, Wavelets and Sparsity XVIII, 111380G (9 September 2019); https://doi.org/10.1117/12.2530342
PROCEEDINGS
13 PAGES


SHARE
Advertisement
Advertisement
Back to Top