| 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 Publication | IEEE ACCESS
 |
| ISSN | 2169-3536 |
| 2019 | |
| Volume | 7Pages:33822-33833 |
| Indexed By | SCI ; EI |
| EI Accession number | 20191506742250 |
| WOS ID | WOS:000463478700001 |
| Contribution Rank | 4 |
| Funding Organization | National 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 |
| Keyword | Convolutional neural network object category recognition ensemble learning transfer learning |
| Abstract | When 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 Subject | Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications |
| WOS Keyword | CONVOLUTIONAL NEURAL-NETWORKS ; IMAGE ; SEGMENTATION |
| WOS Research Area | Computer Science ; Engineering ; Telecommunications |
| Funding Project | 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] ; 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 |
| Identifier | http://ir.sia.cn/handle/173321/24588 |
| Collection | 机器人学研究室 |
| Corresponding Author | Yan F(闫飞) |
| Affiliation | 1.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-SA | View Download | |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment