ONLINE CONVOLUTIONAL DICTIONARY LEARNING

被引：0

作者：

Liu, Jialin ^{[1
]}

Garcia-Cardona, Cristina ^{[2
]}

Wohlberg, Brendt ^{[3
]}

Yin, Wotao ^{[1
]}

机构：

[1] Univ Calif Los Angeles, Dept Math, Los Angeles, CA 90024 USA

[2] Los Alamos Natl Lab, CCS Div, Los Alamos, NM USA

[3] Los Alamos Natl Lab, Theoret Div, Los Alamos, NM USA

来源：

2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2017年

关键词：

Convolutional Sparse Representation; Convolutional Dictionary Learning; ADMM; SPARSE; ALGORITHM;

D O I：

暂无

中图分类号：

TB8 [摄影技术];

学科分类号：

0804 ;

摘要：

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.

引用

页码：1707 / 1711

页数：5

共 16 条

[11] Recursive Least Squares Dictionary Learning Algorithm [J].

Skretting, Karl ;

Engan, Kjersti .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2010, 58 (04) :2121-2130

[12] Fast convolutional sparse coding using matrix inversion lemma [J].

Sorel, Michal ;

Sroubek, Filip .

DIGITAL SIGNAL PROCESSING, 2016, 55 :44-51

[13]

WOHLBERG B, 2016, P IEEE SW S IM AN IN, P57, DOI DOI 10.1109/SSIAI.2016.7459174

[14]

Wohlberg B., 2016, SPARSE OPTIMIZATION

[15] Efficient Algorithms for Convolutional Sparse Representations [J].

Wohlberg, Brendt .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2016, 25 (01) :301-315

[16]

Zeiler MD, 2010, PROC CVPR IEEE, P2528, DOI 10.1109/CVPR.2010.5539957

← 1 2 →