This Article 
 Bibliographic References 
 Add to: 
Invariant Scattering Convolution Networks
Aug. 2013 (vol. 35 no. 8)
pp. 1872-1886
Joan Bruna, Courant Inst., New York Univ., New York, NY, USA
S. Mallat, Ecole Normale Super., Paris, France
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:
wavelet transforms,convolution,Gaussian processes,handwritten character recognition,image classification,image representation,image texture,principal component analysis,support vector machines,generative PCA classifier,invariant scattering convolution networks,wavelet scattering network,translation invariant image representation,deformations,high-frequency information,wavelet transform convolutions,nonlinear modulus,averaging operators,network layer,SIFT-type descriptors,complementary invariant information,mathematical analysis,deep convolution networks,scattering representation,stationary process,Fourier power spectrum,state-of-the-art classification,handwritten digits,texture discrimination,Gaussian kernel SVM,Scattering,Convolution,Fourier transforms,Wavelet coefficients,Computer architecture,wavelets,Classification,convolution networks,deformations,invariants
Joan Bruna, S. Mallat, "Invariant Scattering Convolution Networks," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 8, pp. 1872-1886, Aug. 2013, doi:10.1109/TPAMI.2012.230
Usage of this product signifies your acceptance of the Terms of Use.