A biologically inspired visual integrated model for image classification

被引：14

作者：

Wei, Bing ^{[1
,2
]}

Hao, Kuangrong ^{[1
,2
]}

Gao, Lei ^{[3
,4
]}

Tang, Xue-song ^{[1
,2
]}

Zhao, Yudi ^{[1
,2
]}

机构：

[1] Donghua Univ, Engn Res Ctr Digitized Text & Apparel Technol, Minist Educ, Shanghai 201620, Peoples R China

[2] Donghua Univ, Coll Informat Sci & Technol, 2999 Renmin North Rd, Shanghai 201620, Peoples R China

[3] Shandong Normal Univ, Sch Business, Jinan 250014, Peoples R China

[4] Commonwealth Sci & Ind Res Org CSIRO, Glen Osmond, SA 5064, Australia

来源：

NEUROCOMPUTING | 2020年 / 405卷

基金：

中国国家自然科学基金;

关键词：

CONVOLUTIONAL NEURAL-NETWORK; OBJECT RECOGNITION; DORSAL; DECAY; INFORMATION; STREAMS; AGE;

D O I：

10.1016/j.neucom.2020.04.081

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we propose a biologically inspired visual integrated model for image classification, called VMVI-CNN. Motivated in part by recent neuroscience progress in revealing integrated functions of human visual system, two bio-inspired visual mechanisms (the visual memory decay mechanism and the visual interaction mechanism) are proposed and built within the VMVI-CNN to (1) control the feature information passing through, and (2) increase the richness of feature information. The proposed method is tested on three benchmark datasets (MNIST, Cifar-10, and Mini-ImageNet) and a real-world industrial dataset. The results demonstrate that the new model can extract distinctive features and exhibit a better recognition performance than the current state-of-the-art approaches. © 2020 Elsevier B.V.

引用

页码：103 / 113

页数：11

共 66 条

[21]

Hochreiter S, 1997, NEURAL COMPUT, V9, P1735, DOI [10.1162/neco.1997.9.8.1735, 10.1162/neco.1997.9.1.1, 10.1007/978-3-642-24797-2]

[22] CNN-Based Joint Clustering and Representation Learning with Feature Drift Compensation for Large-Scale Image Data [J].

Hsu, Chih-Chung ;

Lin, Chia-Wen .

IEEE TRANSACTIONS ON MULTIMEDIA, 2018, 20 (02) :421-429

[23] Joint blur kernel estimation and CNN for blind image restoration [J].

Huang, Liqing ;

Xia, Youshen .

NEUROCOMPUTING, 2020, 396 :324-345

[24] Salient object detection via multi-scale attention CNN [J].

Ji, Yuzhu ;

Zhang, Haijun ;

Wu, Q. M. Jonathan .

NEUROCOMPUTING, 2018, 322 :130-140

[25] High-resolution paleovalley classification from airborne electromagnetic imaging and deep neural network training using digital elevation model data [J].

Jiang, Zhenjiao ;

Mallants, Dirk ;

Peeters, Luk ;

Gao, Lei ;

Soerensen, Camilla ;

Mariethoz, Gregoire .

HYDROLOGY AND EARTH SYSTEM SCIENCES, 2019, 23 (06) :2561-2580

[26] ImageNet Classification with Deep Convolutional Neural Networks [J].

Krizhevsky, Alex ;

Sutskever, Ilya ;

Hinton, Geoffrey E. .

COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90

[27] Backpropagation Applied to Handwritten Zip Code Recognition [J].

LeCun, Y. ;

Boser, B. ;

Denker, J. S. ;

Henderson, D. ;

Howard, R. E. ;

Hubbard, W. ;

Jackel, L. D. .

NEURAL COMPUTATION, 1989, 1 (04) :541-551

[28]

Lee CY, 2015, JMLR WORKSH CONF PRO, V38, P562

[29] Too Big to Fail: Large Samples and the p-Value Problem [J].

Lin, Mingfeng ;

Lucas, Henry C., Jr. ;

Shmueli, Galit .

INFORMATION SYSTEMS RESEARCH, 2013, 24 (04) :906-917

[30] Quantisation and pooling method for low-inference-latency spiking neural networks [J].

Lin, Zhitao ;

Shen, Juncheng ;

Ma, De ;

Meng, Jianyi .

ELECTRONICS LETTERS, 2017, 53 (20) :1347-1348

← 1 2 3 4 5 6 7 →