中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 模式分析与学习团队
Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation

文献类型：期刊论文

作者Xie, Guo-Sen1; Zhang, Xu-Yao1; Yan, Shuicheng2; Liu, Cheng-Lin1,3,4
刊名IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
出版日期2017-06-01
卷号27期号:6页码:1263-1274
关键词Convolutional Neural Networks (Cnns) Dictionary Domain ADaptation (Da) Fisher Vector Part Learning Scene Recognition
DOI10.1109/TCSVT.2015.2511543
文献子类Article
英文摘要Convolutional 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.
WOS关键词IMAGE CLASSIFICATION ; KERNEL
WOS研究方向Engineering
语种英语
WOS记录号WOS:000402898600009
资助机构National 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)
源URL[http://ir.ia.ac.cn/handle/173211/11955]  
专题自动化研究所_模式识别国家重点实验室_模式分析与学习团队
通讯作者Xie, Guo-Sen
作者单位1.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
推荐引用方式
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.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。