The Community for Technology Leaders
Green Image
Issue No. 08 - Aug. (2013 vol. 35)
ISSN: 0162-8828
pp: 1872-1886
Joan Bruna , Courant Inst., New York Univ., New York, NY, USA
S. Mallat , Ecole Normale Super., Paris, France
ABSTRACT
A wavelet scattering network computes a translation invariant image representation which is stable to deformations and preserves high-frequency information for classification. It cascades wavelet transform convolutions with nonlinear modulus and averaging operators. The first network layer outputs SIFT-type descriptors, whereas the next layers provide complementary invariant information that improves classification. The mathematical analysis of wavelet scattering networks explains important properties of deep convolution networks for classification. A scattering representation of stationary processes incorporates higher order moments and can thus discriminate textures having the same Fourier power spectrum. State-of-the-art classification results are obtained for handwritten digits and texture discrimination, with a Gaussian kernel SVM and a generative PCA classifier.
INDEX TERMS
Scattering, Convolution, Fourier transforms, Wavelet coefficients, Computer architecture,wavelets, Classification, convolution networks, deformations, invariants
CITATION
Joan Bruna, S. Mallat, "Invariant Scattering Convolution Networks", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 35, no. , pp. 1872-1886, Aug. 2013, doi:10.1109/TPAMI.2012.230
218 ms
(Ver )