CASIA OpenIR  > 模式识别国家重点实验室  > 模式分析与学习
Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation
Xie, Guo-Sen1; Zhang, Xu-Yao1; Yan, Shuicheng2; Liu, Cheng-Lin1,3,4
Source PublicationIEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
2017-06-01
Volume27Issue:6Pages:1263-1274
SubtypeArticle
AbstractConvolutional neural network (CNN) has achieved the state-of-the-art performance in many different visual tasks. Learned from a large-scale training data set, CNN features are much more discriminative and accurate than the handcrafted features. Moreover, CNN features are also transferable among different domains. On the other hand, traditional dictionary-based features (such as BoW and spatial pyramid matching) contain much more local discriminative and structural information, which is implicitly embedded in the images. To further improve the performance, in this paper, we propose to combine CNN with dictionary-based models for scene recognition and visual domain adaptation (DA). Specifically, based on the well-tuned CNN models (e.g., AlexNet and VGG Net), two dictionary-based representations are further constructed, namely, mid-level local representation (MLR) and convolutional Fisher vector (CFV) representation. In MLR, an efficient two-stage clustering method, i.e., weighted spatial and feature space spectral clustering on the parts of a single image followed by clustering all representative parts of all images, is used to generate a class-mixture or a class-specific part dictionary. After that, the part dictionary is used to operate with the multiscale image inputs for generating mid-level representation. In CFV, a multiscale and scale-proportional Gaussian mixture model training strategy is utilized to generate Fisher vectors based on the last convolutional layer of CNN. By integrating the complementary information of MLR, CFV, and the CNN features of the fully connected layer, the state-of-the-art performance can be achieved on scene recognition and DA problems. An interested finding is that our proposed hybrid representation (from VGG net trained on ImageNet) is also complementary to GoogLeNet and/or VGG-11 (trained on Place205) greatly.
KeywordConvolutional Neural Networks (Cnns) Dictionary Domain ADaptation (Da) Fisher Vector Part Learning Scene Recognition
WOS HeadingsScience & Technology ; Technology
DOI10.1109/TCSVT.2015.2511543
WOS KeywordIMAGE CLASSIFICATION ; KERNEL
Indexed BySCI
Language英语
Funding OrganizationNational Basic Research Program of China (973 Program)(2012CB316302) ; Strategic Priority Research Program through the Chinese Academy of Sciences(XDA06040102) ; National Natural Science Foundation of China(61403380)
WOS Research AreaEngineering
WOS SubjectEngineering, Electrical & Electronic
WOS IDWOS:000402898600009
Citation statistics
Cited Times:19[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/11955
Collection模式识别国家重点实验室_模式分析与学习
Corresponding AuthorXie, Guo-Sen
Affiliation1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Natl Univ Singapore, Dept Elect & Comp Engn, Singapore 117583, Singapore
3.Chinese Acad Sci, Inst Automat, Res Ctr Brain Inspired Intelligence, Beijing 100190, Peoples R China
4.Chinese Acad Sci, Inst Automat, CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Xie, Guo-Sen,Zhang, Xu-Yao,Yan, Shuicheng,et al. Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2017,27(6):1263-1274.
APA Xie, Guo-Sen,Zhang, Xu-Yao,Yan, Shuicheng,&Liu, Cheng-Lin.(2017).Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,27(6),1263-1274.
MLA Xie, Guo-Sen,et al."Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 27.6(2017):1263-1274.
Files in This Item: Download All
File Name/Size DocType Version Access License
TCSVT.pdf(5307KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xie, Guo-Sen]'s Articles
[Zhang, Xu-Yao]'s Articles
[Yan, Shuicheng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xie, Guo-Sen]'s Articles
[Zhang, Xu-Yao]'s Articles
[Yan, Shuicheng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xie, Guo-Sen]'s Articles
[Zhang, Xu-Yao]'s Articles
[Yan, Shuicheng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: TCSVT.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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