11 September 2015 Geometric multi-resolution analysis and data-driven convolutions
Author Affiliations +
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.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Nate Strawn, Nate Strawn, } "Geometric multi-resolution analysis and data-driven convolutions", Proc. SPIE 9597, Wavelets and Sparsity XVI, 95971D (11 September 2015); doi: 10.1117/12.2187654; https://doi.org/10.1117/12.2187654


Flaglets for studying the large-scale structure of the Universe
Proceedings of SPIE (September 25 2013)
Uniqueness conditions for low-rank matrix recovery
Proceedings of SPIE (September 13 2011)
Burst erasures and the mean-square error for cyclic frames
Proceedings of SPIE (September 19 2007)
Gabor frames and operator algebras
Proceedings of SPIE (December 03 2000)
Detection of anomalies in an image by wavelet analysis
Proceedings of SPIE (October 31 1993)

Back to Top