Data representation using the Weyl transform

Conference Paper

© 2015 International Conference on Learning Representations, ICLR. All rights reserved. The Weyl transform is introduced as a rich framework for data representation. Transform coefficients are connected to the Walsh-Hadamard transform of multiscale autocorrelations, and different forms of dyadic periodicity in a signal are shown to appear as different features in its Weyl coefficients. The Weyl transform has a high degree of symmetry with respect to a large group of multiscale transformations, which allows compact yet discriminative representations to be obtained by pooling coefficients. The effectiveness of the Weyl transform is demonstrated through the example of textured image classification.

Duke Authors

Cited Authors

  • Qiu, Q; Thompson, A; Calderbank, R; Sapiro, G

Published Date

  • January 1, 2015

Published In

  • 3rd International Conference on Learning Representations, Iclr 2015 Workshop Track Proceedings

Citation Source

  • Scopus