SIA OpenIR  > 机器人学研究室
Using an Ensemble of Incrementally Fine-Tuned CNNs for Cross-Domain Object Category Recognition
Zhang, Xuesong1,2; Yan F(闫飞)1; Zhuang Y( 庄严)1; Hu, Huosheng3; Bu CG(卜春光)4
Department机器人学研究室
Source PublicationIEEE ACCESS
ISSN2169-3536
2019
Volume7Pages:33822-33833
Indexed BySCI ; EI
EI Accession number20191506742250
WOS IDWOS:000463478700001
Contribution Rank4
Funding OrganizationNational Natural Science Foundation of China ; Fundamental Scienti~c Research Project of Liaoning Provincial Department of Education ; National Science Foundation of Liaoning Province of China ; State Key Laboratory of Robotics
KeywordConvolutional neural network object category recognition ensemble learning transfer learning
AbstractWhen the training data is inadequate, it is difficult to train a deep Convolutional Neural Network (CNN) from scratch with randomized initial weights. Instead, it is common to train a source CNN model on a very large data set beforehand, and then use the learned source CNN model as an initialization to train a target CNN model. In deep learning realm, this procedure is called fine-tuning a CNN. This paper presents an experimental study on how to combine a collection of incrementally fine-tuned CNN models for cross-domain and multi-class object category recognition tasks. A group of fine-tuned CNN models is trained on the target data set by incrementally transferring parameters from a source CNN model trained on a large data set initially. The last two fully-connected (FC) layers of the source CNN model are eliminated, and two New FC layers are added to make the learned new CNN model suitable for the target task. Based on Caltech-101 and Office data sets, the experimental results demonstrate the effectiveness and good performance of the proposed methods. The proposed method is more suitable for the object recognition task when there is inadequate target training data.
Language英语
WOS SubjectComputer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS KeywordCONVOLUTIONAL NEURAL-NETWORKS ; IMAGE ; SEGMENTATION
WOS Research AreaComputer Science ; Engineering ; Telecommunications
Funding ProjectNational Natural Science Foundation of China[61503056] ; National Natural Science Foundation of China[U1508208] ; Fundamental Scienti~c Research Project of Liaoning Provincial Department of Education[JDL2017017] ; National Science Foundation of Liaoning Province of China[20180551020] ; State Key Laboratory of Robotics[2017-O15] ; National Natural Science Foundation of China[61503056] ; National Natural Science Foundation of China[U1508208] ; Fundamental Scienti~c Research Project of Liaoning Provincial Department of Education[JDL2017017] ; National Science Foundation of Liaoning Province of China[20180551020] ; State Key Laboratory of Robotics[2017-O15]
Citation statistics
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/24588
Collection机器人学研究室
Corresponding AuthorYan F(闫飞)
Affiliation1.School of Control Science and Engineering, Dalian University of Technology, Dalian 116024, China
2.Software Technology Institute, Dalian Jiaotong University, Dalian 116028, China
3.School of Computer Science and Electronic Engineering, University of Essex, Colchester CO4 3SQ, U.K.
4.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
Recommended Citation
GB/T 7714
Zhang, Xuesong,Yan F,Zhuang Y,et al. Using an Ensemble of Incrementally Fine-Tuned CNNs for Cross-Domain Object Category Recognition[J]. IEEE ACCESS,2019,7:33822-33833.
APA Zhang, Xuesong,Yan F,Zhuang Y,Hu, Huosheng,&Bu CG.(2019).Using an Ensemble of Incrementally Fine-Tuned CNNs for Cross-Domain Object Category Recognition.IEEE ACCESS,7,33822-33833.
MLA Zhang, Xuesong,et al."Using an Ensemble of Incrementally Fine-Tuned CNNs for Cross-Domain Object Category Recognition".IEEE ACCESS 7(2019):33822-33833.
Files in This Item: Download All
File Name/Size DocType Version Access License
Using an Ensemble of(3868KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang, Xuesong]'s Articles
[Yan F(闫飞)]'s Articles
[Zhuang Y( 庄严)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang, Xuesong]'s Articles
[Yan F(闫飞)]'s Articles
[Zhuang Y( 庄严)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang, Xuesong]'s Articles
[Yan F(闫飞)]'s Articles
[Zhuang Y( 庄严)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Using an Ensemble of Incrementally Fine-Tuned CNNs for Cross-Domain Object Category Recognition.pdf
Format: Adobe PDF
This file does not support browsing at this time
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.