Deakin University
Browse

File(s) under permanent embargo

A frequency domain neural network for fast image super-resolution

conference contribution
posted on 2018-01-01, 00:00 authored by Junxuan Li, Shaodi You, Antonio Robles-KellyAntonio Robles-Kelly
In this paper, we present a frequency domain neural network for image super-resolution. The network employs the convolution theorem so as to cast convolutions in the spatial domain as products in the frequency domain. Moreover, the non-linearity in deep nets, of ten achieved by a rectifier unit, is here cast as a convolution in the frequency domain. This not only yields a network which is very computationally efficient at testing, but also one whose parameters can all be learnt accordingly. The network can be trained using back propagation and is devoid of complex numbers due to the use of the Hartley transform as an alternative to the Fourier transform. Moreover, the network is potentially applicable to other problems elsewhere in computer vision and image processing which are of ten cast in the frequency domain. We show results on super-resolution and compare against alternatives elsewhere in the literature. In our experiments, our network is one to two orders of magnitude faster than the alternatives with a marginal loss of performance.

History

Event

Neural Networks. Joint Conference (2018 : Rio de Janeiro, Brazil)

Pagination

1 - 8

Publisher

IEEE

Location

Rio de Janeiro, Brazil

Place of publication

Piscataway, N.J.

Start date

2018-07-08

End date

2018-07-13

ISSN

2161-4407

ISBN-13

9781509060146

Language

eng

Publication classification

E1.1 Full written paper - refereed

Title of proceedings

IJCNN 2018 : Proceedings of the International Joint Conference on Neural Networks