Share Email Print
cover

Proceedings Paper • new

Structured receptive field networks and applications to hyperspectral image classification
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Deep neural networks have achieved impressive performance in problems of object detection and object category classifications. To perform efficiently though, such methods typically require a large number of training samples. Unfortunately, this requirement is highly impractical or impossible in applications such as hyperspectral classification where it is expensive and labor intensive to generate labeled data for training. A few ideas have been proposed in the literature to address this problem such as transfer learning and domain adaptation. In this work, we propose an alternative strategy to reduce the number of network parameters based on Structured Receptive Field Networks (SRFN), a class of convolutional neural networks (CNNs) where each convolutional filter is a linear combination from a predefined dictionary. To better exploit the characteristics of hyperspectral data to be learned, we choose a filter dictionary consisting of directional filters inspired by the theory of shearlets and we train a SRFN by imposing that the convolutional filters form sparse linear combinations in such dictionary. The application of our SRFN to problems of hyperspectral classification shows that this approach achieves very competitive performance as compared to conventional CNNs.

Paper Details

Date Published: 9 September 2019
PDF: 9 pages
Proc. SPIE 11138, Wavelets and Sparsity XVIII, 111380O (9 September 2019); doi: 10.1117/12.2527712
Show Author Affiliations
Demetrio Labate, Univ. of Houston (United States)
Kazem Safari, Univ. of Houston (United States)
Nikolaos Karantzas, Univ. of Houston (United States)
Saurabh Prasad, Univ. of Houston (United States)
Farideh Foroozandeh Shahraki, Univ. of Houston (United States)


Published in SPIE Proceedings Vol. 11138:
Wavelets and Sparsity XVIII
Dimitri Van De Ville; Manos Papadakis; Yue M. Lu, Editor(s)

© SPIE. Terms of Use
Back to Top