| Image-Specific Classification With Local and Global Discriminations | |
Zhang CJ(张淳杰) ; Cheng J(程健); Li ZS(李长升); Tian Q(田奇)
| |
| Source Publication | IEEE Transactions on Neural Networks and Learning Systems
 |
| 2017 | |
| Issue | 0Pages:0 |
| Abstract | Most image classification methods try to learn classifiers for each class using training images alone. Due to the inter-class and intra-class variations, it would be more effective to take the testing images into consideration for classifier learning. In this brief, we proposes a novel image-specific classification method by combing the local and global discriminations of training images. We adaptively train classifier for each testing image instead of generating classifiers for each class with training images alone. For each testing image, we first select its \emph{k} nearest neighbors in the training set with the corresponding labels for local classifier training. This helps to model the distinctive characters of each testing image. Besides, we also use all the training images for global discrimination modeling. The local and global discriminations are combined for final classification. In this way, we could not only model the specific character of each testing image but also avoid the local optimum by jointly considering all the training images. To evaluate the usefulness of the proposed image-specific classification with local and global discriminations method (ISC-LG), we conduct image classification experiments on several public image datasets. The superior performances over other baseline methods prove the effectiveness of the proposed ISC-LG method. |
| Keyword | Image-specific Classification Global Information Local Information Object Categorization |
| DOI | 10.1109/TNNLS.2017.2748952 |
| WOS ID | WOS:000443083700045 |
| Citation statistics | |
| Document Type | 期刊论文 |
| Identifier | http://ir.ia.ac.cn/handle/173211/15318 |
| Collection | 类脑智能研究中心 |
| Affiliation | 1.Research Center for Brain-inspired Intelligence, Institute of Automation, Chinese Academy of Sciences, 100190, Beijing, China 2.University of Chinese Academy of Sciences, 100049, Beijing, China. 3.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, P.O.Box 2728, Beijing, China 4.School of Computer Science and Engineering, University of Electronic Science and Technology of China. 5.Department of Computer Sciences, University of Texas at San Antonio. TX, 78249, U.S.A. |
| Recommended Citation GB/T 7714 | Zhang CJ,Cheng J,Li ZS,et al. Image-Specific Classification With Local and Global Discriminations[J]. IEEE Transactions on Neural Networks and Learning Systems,2017(0):0. |
| APA | Zhang CJ,Cheng J,Li ZS,&Tian Q.(2017).Image-Specific Classification With Local and Global Discriminations.IEEE Transactions on Neural Networks and Learning Systems(0),0. |
| MLA | Zhang CJ,et al."Image-Specific Classification With Local and Global Discriminations".IEEE Transactions on Neural Networks and Learning Systems .0(2017):0. |
| Files in This Item: | Download All | |||||
| File Name/Size | DocType | Version | Access | License | ||
| FINAL VERSION.pdf（571KB） | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | View Download | |
| tnnls Image-Specific（151KB） | 开放获取 | -- | View Download | |||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment