Online Convolutional Sparse Coding with Sample-Dependent Dictionary
Yaqing Wang, Quanming Yao, James Tin-Yau Kwok, Lionel M. NI
Abstract
Convolutional sparse coding (CSC) has been popularly used for the learning of shift-invariant dictionaries in image and signal processing. However, existing methods have limited scalability. In this paper, instead of convolving with a dictionary shared by all samples, we propose the use of a sample-dependent dictionary in which each filter is a linear combination of a small set of base filters learned from data. This added flexibility allows a large number of sample-dependent patterns to be captured, which is especially useful in the handling of large or high-dimensional data sets. Computationally, the resultant model can be efficiently learned by online learning. Extensive experimental results on a number of data sets show that the proposed method outperforms existing CSC algorithms with significantly reduced time and space complexities.
BibTeX
@InProceedings{pmlr-v80-wang18k,
title = {Online Convolutional Sparse Coding with Sample-Dependent Dictionary},
author = {Wang, Yaqing and Yao, Quanming and Kwok, James Tin-Yau and NI, Lionel M.},
booktitle = {Proceedings of the 35th International Conference on Machine Learning},
pages = {5209--5218},
year = {2018},
editor = {Dy, Jennifer and Krause, Andreas},
volume = {80},
series = {Proceedings of Machine Learning Research},
month = {10--15 Jul},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v80/wang18k/wang18k.pdf},
url = {https://proceedings.mlr.press/v80/wang18k.html},
abstract = {Convolutional sparse coding (CSC) has been popularly used for the learning of shift-invariant dictionaries in image and signal processing. However, existing methods have limited scalability. In this paper, instead of convolving with a dictionary shared by all samples, we propose the use of a sample-dependent dictionary in which each filter is a linear combination of a small set of base filters learned from data. This added flexibility allows a large number of sample-dependent patterns to be captured, which is especially useful in the handling of large or high-dimensional data sets. Computationally, the resultant model can be efficiently learned by online learning. Extensive experimental results on a number of data sets show that the proposed method outperforms existing CSC algorithms with significantly reduced time and space complexities.}
}