Published on Wed Jun 21 2017

Scalable Online Convolutional Sparse Coding

Yaqing Wang, Quanming Yao, James T. Kwok, Lionel M. Ni

Convolutional sparse coding (CSC) improves sparse coding by learning ashift-invariant dictionary from the data. Theoretical analysis shows that the learned Dictionary converges to a stationary point of the optimization problem. The proposed method can handle at least ten times more images.

0
0
0
Abstract

Convolutional sparse coding (CSC) improves sparse coding by learning a shift-invariant dictionary from the data. However, existing CSC algorithms operate in the batch mode and are expensive, in terms of both space and time, on large datasets. In this paper, we alleviate these problems by using online learning. The key is a reformulation of the CSC objective so that convolution can be handled easily in the frequency domain and much smaller history matrices are needed. We use the alternating direction method of multipliers (ADMM) to solve the resulting optimization problem and the ADMM subproblems have efficient closed-form solutions. Theoretical analysis shows that the learned dictionary converges to a stationary point of the optimization problem. Extensive experiments show that convergence of the proposed method is much faster and its reconstruction performance is also better. Moreover, while existing CSC algorithms can only run on a small number of images, the proposed method can handle at least ten times more images.

Fri Apr 27 2018
Computer Vision
Online Convolutional Sparse Coding with Sample-Dependent Dictionary
Convolutional sparse coding (CSC) has been popularly used for the learning of shift-invariant dictionaries in image and signal processing. We propose a sample-dependent dictionary in which filters are obtained as linear combinations of a small set of base filters learned from the data.
0
0
0
Thu Aug 31 2017
Machine Learning
First and Second Order Methods for Online Convolutional Dictionary Learning
Convolutional sparse representations are a form of sparse representation with a structured, translation invariant dictionary. Most convolutional dictionary learning algorithms to date operate in batch mode, requiring simultaneous access to all training images during the learning process.
0
0
0
Tue Sep 07 2021
Machine Learning
Efficient ADMM-based Algorithms for Convolutional Sparse Coding
Convolutional sparse coding improves on the standard sparse approximation by incorporating a global shift-invariant model. The most efficient convolutional sparse coding methods are based on the alternating direction method of multipliers and the convolution theorem. This letter presents a solution to this subproblem.
0
0
0
Sat Sep 09 2017
Machine Learning
Convolutional Dictionary Learning: A Comparative Review and New Algorithms
Convolutional sparse representations are a form of sparse representation with a structure that is equivalent to convolution with a set of linear filters. effective algorithms have recently been developed for the convolutional dense coding problem. The corresponding dictionary learning problem is substantially more challenging.
0
0
0
Sat Aug 31 2019
Machine Learning
Stochastic Convolutional Sparse Coding
State-of-the-art methods for Convolutional Sparse Coding usually employ Fourier-domain solvers in order to speed up the convolution operators. In this work, we propose a novel stochastic.spatial- domain solver in which a randomized
0
0
0
Sun Apr 08 2018
Computer Vision
Supervised Convolutional Sparse Coding
convolutional sparse coding aims at learning discriminative dictionaries instead of purely reconstructive ones. We incorporate a supervised regularization term into the traditional unsupervised CSC objective to encourage the final dictionary elements to be discriminatives.
0
0
0