A Multi-layer Convolutional Sparse Coding Network Based on Multi-Scale

Xie Wei-li; Zhang Jun

doi:10.12052/gdutxb.230205

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

A Multi-layer Convolutional Sparse Coding Network Based on Multi-Scale

更新时间：2026-05-27

- A Multi-layer Convolutional Sparse Coding Network Based on Multi-Scale
- Vol. 41, Issue 6, Pages: 125-132(2024)
- 作者机构：
  
  广东工业大学信息工程学院,广东,广州,510006
- 作者简介：
- 基金信息：
- DOI：10.12052/gdutxb.230205
  CLC： TP391
- Published：2024
- 稿件说明：
移动端阅览
谢伟立, 张军. 一种基于多尺度的多层卷积稀疏编码网络[J]. 广东工业大学学报, 2024, 41(6): 125-132.

Xie Wei-li, Zhang Jun. A Multi-layer Convolutional Sparse Coding Network Based on Multi-Scale[J]. 2024, 41(6): 125-132.
谢伟立, 张军. 一种基于多尺度的多层卷积稀疏编码网络[J]. 广东工业大学学报, 2024, 41(6): 125-132. DOI： 10.12052/gdutxb.230205.

Xie Wei-li, Zhang Jun. A Multi-layer Convolutional Sparse Coding Network Based on Multi-Scale[J]. 2024, 41(6): 125-132. DOI： 10.12052/gdutxb.230205.

摘要

多层卷积稀疏编码模型(Multi-layer Convolutional Sparse Coding

ML-CSC)被认为是对卷积神经网络(Convolutional Neural Networks

CNN)的一种理论阐释。尽管ML-CSC模型在特征对比度高的数据集上表现良好，但是其在特征对比度低的数据集上表现不佳。为了解决这一问题，本文引入多尺度技术设计了一种多尺度多层卷积稀疏编码网络(Multi-scale Multi-layer Convolutional Sparse Coding Network

MSMCSCNet)，不仅在特征对比度较弱的情况下得到更好的图像分类效果，而且也使模型具有扎实的理论基础和较高的可解释性。实验结果表明，MSMCSCNet在不增加参数量的前提下，在Cifar10、Cifar100数据集和Imagenet32数据子集上，准确率相比现有ML-CSC模型分别提高了5.75，9.75和9.8个百分点。此外，消融实验进一步证实了模型的多尺度设计和特征筛选模式设计的有效性。

Abstract

In recent years

the Multi-layer convolutional sparse coding (ML-CSC) model has been regarded as a theoretical explanation for convolutional neural networks (CNN). While the ML-CSC model performs well on datasets with high feature contrast

its performance is not satisfactory on datasets with low feature contrast. To address this issue

this paper introduces a multi-scale technique to design a multi-scale multi-layer convolutional sparse coding network (MSMCSCNet)

which not only achieves better image classification results in scenarios with weak feature contrast

but also provides the model with a solid theoretical foundation and higher interpretability. Experimental results demonstrate that

without increasing the parameter count

MSMCSCNet achieves accuracy improvements of 5.75

9.75

and 9.8 percentage points on the Cifar10

Cifar100 datasets

and the Imagenet32 subset

respectively

compared to existing ML-CSC models. Furthermore

ablation experiments further validate the effectiveness of the model's multi-scale design and feature selection mechanism.

关键词

Keywords

references

LECUN Y, BENGIO Y, HINTON G. Deep learning [J]. Nature, 2015, 521(7553): 436-444.

NERCESSIAN S C, PANETTA K A, AGAIAN S S. Non-linear direct multi-scale image enhancement based on the luminance and contrast masking characteristics of the human visual system [J]. IEEE Transactions on Image Processing, 2013, 22(9): 3549-3561.

PAPYAN V, ROMANO Y, ELAD M. Convolutional neural networks analyzed via convolutional sparse coding [J]. The Journal of Machine Learning Research, 2017, 18(1): 2887-2938.

SULAM J, ABERDAM A, BECK A, et al . On multi-layer basis pursuit, efficient algorithms and convolutional neural networks [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 42(8): 1968-1980.

PAPYAN V, SULAM J, ELAD M. Working locally thinking globally: theoretical guarantees for convolutional sparse coding [J]. IEEE Transactions on Signal Processing, 2017, 65(21): 5687-5701.

CHEN S S, DONOHO D L, SAUNDERS M A. Atomic decomposition by basis pursuit [J]. SIAM Review, 2001, 43(1): 129-159.

TROPP J A, GILBERT A C. Signal recovery from random measurements via orthogonal matching pursuit [J]. IEEE Transactions on Information Theory, 2007, 53(12): 4655-4666.

DAUBECHIES I, DEFRISE M, DE MOL C. An iterative thresholding algorithm for linear inverse problems with a sparsity constraint [J]. Communications on Pure and Applied Mathematics:A Journal Issued by the Courant Institute of Mathematical Sciences, 2004, 57(11): 1413-1457.

BECK A, TEBOULLE M. A fast iterative shrinkage-thresholding algorithm for linear inverse problems [J]. SIAM Journal on Imaging Sciences, 2009, 2(1): 183-202.

BOYD S, PARIKH N, CHU E, et al . Distributed optimization and statistical learning via the alternating direction method of multipliers [J ] . Foundations and Trends® in Machine Learning, 2011, 3(1): 1-122.

SIMON D, ELAD M. Rethinking the CSC model for natural images[J]. Advances in Neural Information Processing Systems, 2019(204): 2274-2284.

GUO P, ZENG D, TIAN Y, et al . Multi-scale enhancement fusion for underwater sea cucumber images based on human visual system modelling [J ] . Computers and Electronics in Agriculture, 2020, 175: 105608.

KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks [J]. Communications of the ACM, 2017, 60(6): 84-90.

OLIMOV B, SUBRAMANIAN B, UGLI R A A, et al . Consecutive multiscale feature learning-based image classification model [J ] . Scientific Reports, 2023, 13(1): 3595.

NATARAJAN B K. Sparse approximate solutions to linear systems [J]. SIAM Journal on Computing, 1995, 24(2): 227-234.

CANDÈS E J, ROMBERG J, TAO T. Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information [J]. IEEE Transactions on Information Theory, 2006, 52(2): 489-509.

TIBSHIRANI R. Regression shrinkage and selection via the lasso [J]. Journal of the Royal Statistical Society Series B:Statistical Methodology, 1996, 58(1): 267-288.

DONOHO D L, ELAD M. Optimally sparse representation in general (nonorthogonal) dictionaries via ℓ1 minimization [J]. Proceedings of the National Academy of Sciences, 2003, 100(5): 2197-2202.

RUBINSTEIN R, ZIBULEVSKY M, ELAD M. Double sparsity: learning sparse dictionaries for sparse signal approximation [J]. IEEE Transactions on Signal Processing, 2009, 58(3): 1553-1564.

TROPP J A. Greed is good: algorithmic results for sparse approximation [J]. IEEE Transactions on Information theory, 2004, 50(10): 2231-2242.

GROHS P. Mathematical aspects of deep learning[M]. Cambridge England: Cambridge University Press, 2022: 1-111.

LI M, ZHAI P, TONG S, et al . Revisiting sparse convolutional model for visual recognition [J ] . Advances in Neural Information Processing Systems, 2022, 35: 10492-10504.

ZHANG Z, ZHANG S. Towards understanding residual and dilated dense neural networks via convolutional sparse coding [J]. National Science Review, 2021, 8(3): nwaa159.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Local Orthogonal Feature Fusion for Few-Shot Image Classification

An Insulator Burst Defect Detection Method Based on YOLOv4-MP

A Research on Deep Learning Object Detection Algorithm Based on Feature Fusion

A Review and Thinking of Deep Learning with a Restricted Number of Samples

The Cross-twin Physics-informed Neural Network for Wave Equations with Conserved Quantities

Related Author

Wu Huidong

Liu Licheng

Li Jianze

Huang Guo-heng

Cheng Liang-lun

Tu Ze-liang

Lin Zhi-yi

Xie Guo-bo

Related Institution

School of Computer Science and Technology, Guangdong University of Technology

Yunnan Electric Power Research Institute, Yunnan Power Grid Co., Ltd

School of Applied Mathematics, Guangdong University of Technology

School of Automation, Guangdong University of Technology

School of Computers, Guangdong University of Technology

AI问答

⁰