Invariant Scattering Convolution Networks

Details Invariant Scattering Convolution Networks Invariant Scattering Convolution Networks

2012-03-05

arxiv.org/abs/1203.1513v2

Computer Science

Computer Vision and Pattern Recognition

15 pages double column, 9 figures

Scientific paper

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 non-linear modulus and averaging operators. The first network layer outputs SIFT-type descriptors whereas the next layers provide complementary invariant information which 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, using a Gaussian kernel SVM and a generative PCA classifier.

Affiliated with

Also associated with

No associations

Rating

Invariant Scattering Convolution Networks does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Invariant Scattering Convolution Networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Invariant Scattering Convolution Networks will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-134168