English

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.

Keywords

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