Fast convolutional sparse coding using matrix inversion lemma

0459332 - ÚTIA 2017 RIV NL eng J - Journal Article
Šorel, Michal - Šroubek, Filip
Fast convolutional sparse coding using matrix inversion lemma.
Digital Signal Processing. Roč. 55, č. 1 (2016), s. 44-51. ISSN 1051-2004. E-ISSN 1095-4333
R&D Projects: GA ČR GA13-29225S
Institutional support: RVO:67985556
Keywords : Convolutional sparse coding * Feature learning * Deconvolution networks * Shift-invariant sparse coding
Subject RIV: JD - Computer Applications, Robotics
Impact factor: 2.337, year: 2016
http://library.utia.cas.cz/separaty/2016/ZOI/sorel-0459332.pdf

Convolutional sparse coding is an interesting alternative to standard sparse coding in modeling shift-invariant signals, giving impressive results for example in unsupervised learning of visual features. In state-of-the-art methods, the most time-consuming parts include inversion of a linear operator related to convolution. In this article we show how these inversions can be computed non-iteratively in the Fourier domain using the matrix inversion lemma. This greatly speeds up computation and makes convolutional sparse coding computationally feasible even for large problems. The algorithm is derived in three variants, one of them especially suitable for parallel implementation. We demonstrate algorithms on two-dimensional image data but all results hold for signals of arbitrary dimension.
Permanent Link: http://hdl.handle.net/11104/0259700