Online Convolutional Dictionary Learning
Machine Learning
2018-02-26 v2 Computer Vision and Pattern Recognition
Image and Video Processing
Abstract
While a number of different algorithms have recently been proposed for convolutional dictionary learning, this remains an expensive problem. The single biggest impediment to learning from large training sets is the memory requirements, which grow at least linearly with the size of the training set since all existing methods are batch algorithms. The work reported here addresses this limitation by extending online dictionary learning ideas to the convolutional context.
Cite
@article{arxiv.1706.09563,
title = {Online Convolutional Dictionary Learning},
author = {Jialin Liu and Cristina Garcia-Cardona and Brendt Wohlberg and Wotao Yin},
journal= {arXiv preprint arXiv:1706.09563},
year = {2018}
}
Comments
Accepted to be presented at ICIP 2017