Online Convolutional Dictionary Learning

08/31/2017
by   Jialin Liu, et al.
0

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, which results in very high memory usage and severely limits the training data that can be used. Very recently, however, a number of authors have considered the design of online convolutional dictionary learning algorithms that offer far better scaling of memory and computational cost with training set size than batch methods. This paper extends our prior work, improving a number of aspects of our previous algorithm; proposing an entirely new one, with better performance, and that supports the inclusion of a spatial mask for learning from incomplete data; and providing a rigorous theoretical analysis of these methods.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 21

page 22

03/06/2015

On the Invariance of Dictionary Learning and Sparse Representation to Projecting Data to a Discriminative Space

In this paper, it is proved that dictionary learning and sparse represen...
09/09/2017

Convolutional Dictionary Learning

Convolutional sparse representations are a form of sparse representation...
01/13/2017

Dictionary Learning from Incomplete Data

This paper extends the recently proposed and theoretically justified ite...
01/15/2017

Boosting Dictionary Learning with Error Codes

In conventional sparse representations based dictionary learning algorit...
12/18/2014

Example Selection For Dictionary Learning

In unsupervised learning, an unbiased uniform sampling strategy is typic...
05/23/2018

Dictionary Learning by Dynamical Neural Networks

A dynamical neural network consists of a set of interconnected neurons t...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.