SCATTERING CONVOLUTION NETWORKS and DUAL-TREE WAVELETS
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Prof. Ramji Venkataramanan.
I will talk about the joint project that I researched with Anton van den Hengel of the University of Adelaide between July and November 2013. The project is based on integrating dual-tree complex wavelets into new deep network structures for visual learning tasks, that have been proposed by Stephane Mallat of Ecole Polytechnique, Paris. We will discuss the basic ideas behind Invariant Scattering Networks and show how an efficient implementation can be achieved using dual-tree wavelets. I will present some of our own results from using the algorithm to classify MNIST hand-written digits and also digits from the Google Street-View House Number dataset. The ideas behind Scattering Nets are introduced in the following paper:
http://www.cmap.polytechnique.fr/scattering/pami-final.pdf “Invariant Scattering Convolution Networks”,
by Joan Bruna and Stephane Mallat of CMAP , Ecole Polytechnique, Palaiseau, France, in IEEE Trans. on PAMI , August 2013.
This talk is part of the Signal Processing and Communications Lab Seminars series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|