Deep Roto-Translation Scattering for Object Classification

Edouard Oyallon, Stephane Mallat; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 2865-2873

Abstract


Dictionary learning algorithms or supervised deep convolution networks have considerably improved the efficiency of predefined feature representations such as SIFT. We introduce a deep scattering convolution network, with predefined wavelet filters over spatial and angular variables. This representation brings an important improvement to results previously obtained with predefined features over object image databases such as Caltech and CIFAR. The resulting accuracy is comparable to results obtained with unsupervised deep learning and dictionary based representations. This shows that refining image representations by using geometric priors is a promising direction to improve image classification and its understanding.

Related Material


[pdf]
[bibtex]
@InProceedings{Oyallon_2015_CVPR,
author = {Oyallon, Edouard and Mallat, Stephane},
title = {Deep Roto-Translation Scattering for Object Classification},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}