Share Email Print
cover

Proceedings Paper • new

Sheared multi-scale weight sharing for multi-spectral superresolution
Author(s): Micah Goldblum; Liam Fowl; Wojciech Czaja
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Deep learning approaches to single-image superresolution typically use convolutional neural networks. Convolutional layers introduce translation invariance to neural networks. However, other spatial invariants appear in imaging data. Two such invariances are scale invariance, similar features at multiple spacial scales, and shearing invariance. We investigate these invariances by using weight sharing between dilated and sheared convolutional kernels in the context of multi-spectral imaging data. Traditional pooling methods can extract features at coarse spacial levels. Our approach explores a finer range of scales. Additionally, our approach offers improved storage efficiency because dilated and sheared convolutions allows single trainable kernels to extract information at multiple spacial scales and shears without the costs of training and storing many filters, especially in multi-spectral imaging where data representations are complex.

Paper Details

Date Published: 14 May 2019
PDF: 9 pages
Proc. SPIE 10986, Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV, 109860X (14 May 2019); doi: 10.1117/12.2519982
Show Author Affiliations
Micah Goldblum, Univ. of Maryland, College Park (United States)
Liam Fowl, Univ. of Maryland, College Park (United States)
Wojciech Czaja, Univ. of Maryland, College Park (United States)


Published in SPIE Proceedings Vol. 10986:
Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV
Miguel Velez-Reyes; David W. Messinger, Editor(s)

© SPIE. Terms of Use
Back to Top