Share Email Print

Proceedings Paper

Geometric multi-resolution analysis and data-driven convolutions
Author(s): Nate Strawn
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We introduce a procedure for learning discrete convolutional operators for generic datasets which recovers the standard block convolutional operators when applied to sets of natural images. They key observation is that the standard block convolutional operators on images are intuitive because humans naturally understand the grid structure of the self-evident functions over images spaces (pixels). This procedure first constructs a Geometric Multi-Resolution Analysis (GMRA) on the set of variables giving rise to a dataset, and then leverages the details of this data structure to identify subsets of variables upon which convolutional operators are supported, as well as a space of functions that can be shared coherently amongst these supports.

Paper Details

Date Published: 11 September 2015
PDF: 7 pages
Proc. SPIE 9597, Wavelets and Sparsity XVI, 95971D (11 September 2015); doi: 10.1117/12.2187654
Show Author Affiliations
Nate Strawn, Georgetown Univ. (United States)

Published in SPIE Proceedings Vol. 9597:
Wavelets and Sparsity XVI
Manos Papadakis; Vivek K. Goyal; Dimitri Van De Ville, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?