Online Convolutional Sparse Coding with Sample-Dependent Dictionary

Yaqing Wang, Quanming Yao, James Tin-Yau Kwok, Lionel M. NI
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:5209-5218, 2018.

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.

Cite this Paper


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.} }
Endnote
%0 Conference Paper %T Online Convolutional Sparse Coding with Sample-Dependent Dictionary %A Yaqing Wang %A Quanming Yao %A James Tin-Yau Kwok %A Lionel M. NI %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-wang18k %I PMLR %P 5209--5218 %U https://proceedings.mlr.press/v80/wang18k.html %V 80 %X 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.
APA
Wang, Y., Yao, Q., Kwok, J.T. & NI, L.M.. (2018). Online Convolutional Sparse Coding with Sample-Dependent Dictionary. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:5209-5218 Available from https://proceedings.mlr.press/v80/wang18k.html.

Related Material