期刊
APPLIED MATHEMATICAL MODELLING
卷 95, 期 -, 页码 644-666出版社
ELSEVIER SCIENCE INC
DOI: 10.1016/j.apm.2021.02.023
关键词
Convolutional coding; Convolutional dictionary learning; Online dictionary learning; Gradient descent flow
资金
- National Natural Science Foundation of China [12001381, 61871274, 61801305]
- China Postdoctoral Science Foundation [2018M64081]
- Peacock Plan [KQTD2016053112051497]
- Shenzhen Key Basic Research Project [JCYJ20180507184647636, JCYJ20170412104656685, JCYJ20170818094109846, JCYJ20190808155618806]
- Chongqing Natural Science Foundation of China [cstc2019jcyj-msxmX0060]
- key project of science and technology research program of Chongqing Education Commission of China [KJZD-K202001503]
This paper introduces a noise-robust online convolutional coding model for image representation, which employs an alternating algorithm to tackle the image pursuit and dictionary learning problems. Experimental results demonstrate that the proposed method can generate more meaningful feature representations compared to existing models when the training data is corrupted by Poisson noise.
In this paper, we propose a noise-robust online convolutional coding model for image representation, which can use the noisy images as training data. Then an alternating algorithm is utilized to convert the model into two sub-problems, the image pursuit problem and the dictionary learning problem. For the image pursuit problem, the Gauss elimination method is used to solve the equation set which is derived by the Euler equation and discrete Fourier transform. For the dictionary learning problem, a gradient-descent flow is derived to solve it. Experimental results show that our method can output more meaningful feature representations compared to the related models while the training data was corrupted by Poisson noise. (c) 2021 Elsevier Inc. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据