Sheared multi-scale weight sharing for multi-spectral superresolution

Micah Goldblum; Liam Fowl; Wojciech Czaja

doi:10.1117/12.2519982

14 May 2019 Sheared multi-scale weight sharing for multi-spectral superresolution

Micah Goldblum, Liam Fowl, Wojciech Czaja

Proceedings Volume 10986, Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV; 109860X (2019) https://doi.org/10.1117/12.2519982
Event: SPIE Defense + Commercial Sensing, 2019, Baltimore, MD, United States

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.

Citation Download Citation

Micah Goldblum, Liam Fowl, and Wojciech Czaja "Sheared multi-scale weight sharing for multi-spectral superresolution", Proc. SPIE 10986, Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV, 109860X (14 May 2019); https://doi.org/10.1117/12.2519982

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