CoLR: Classification-Oriented Local Representation for Image Recognition
Naïve sparse representation has stability problem due to its unsupervised nature, which is not preferred for classification tasks. For this problem, this paper presents a novel representation learning method named classification-oriented local representation (CoLR) for image recognition. The core id...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2019/7835797 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832564119459332096 |
|---|---|
| author | Tan Guo Lei Zhang Xiaoheng Tan Liu Yang Zhiwei Guo Fupeng Wei |
| author_facet | Tan Guo Lei Zhang Xiaoheng Tan Liu Yang Zhiwei Guo Fupeng Wei |
| author_sort | Tan Guo |
| collection | DOAJ |
| description | Naïve sparse representation has stability problem due to its unsupervised nature, which is not preferred for classification tasks. For this problem, this paper presents a novel representation learning method named classification-oriented local representation (CoLR) for image recognition. The core idea of CoLR is to find the most relevant training classes and samples with test sample by taking the merits of class-wise sparseness weighting, sample locality, and label prior. The proposed representation strategy can not only promote a classification-oriented representation, but also boost a locality adaptive representation within the selected training classes. The CoLR model is efficiently solved by Augmented Lagrange Multiplier (ALM) scheme based on a variable splitting strategy. Then, the performance of the proposed model is evaluated on benchmark face datasets and deep object features. Specifically, the deep features of the object dataset are obtained by a well-trained convolutional neural network (CNN) with five convolutional layers and three fully connected layers on the challenging ImageNet. Extensive experiments verify the superiority of CoLR in comparison with some state-of-the-art models. |
| format | Article |
| id | doaj-art-45443ea7166e49eb8ca936fe0eeed6f5 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2019-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-45443ea7166e49eb8ca936fe0eeed6f52025-02-03T01:11:43ZengWileyComplexity1076-27871099-05262019-01-01201910.1155/2019/78357977835797CoLR: Classification-Oriented Local Representation for Image RecognitionTan Guo0Lei Zhang1Xiaoheng Tan2Liu Yang3Zhiwei Guo4Fupeng Wei5School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaSchool of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, ChinaSchool of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, ChinaSchool of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaChongqing Engineering Laboratory for Detection, Control and Integrated System, Chongqing Technology and Business University, Chongqing 400067, ChinaSchool of Instrumentation Science and Engineering, Harbin Institute of Technology, Harbin 150001, ChinaNaïve sparse representation has stability problem due to its unsupervised nature, which is not preferred for classification tasks. For this problem, this paper presents a novel representation learning method named classification-oriented local representation (CoLR) for image recognition. The core idea of CoLR is to find the most relevant training classes and samples with test sample by taking the merits of class-wise sparseness weighting, sample locality, and label prior. The proposed representation strategy can not only promote a classification-oriented representation, but also boost a locality adaptive representation within the selected training classes. The CoLR model is efficiently solved by Augmented Lagrange Multiplier (ALM) scheme based on a variable splitting strategy. Then, the performance of the proposed model is evaluated on benchmark face datasets and deep object features. Specifically, the deep features of the object dataset are obtained by a well-trained convolutional neural network (CNN) with five convolutional layers and three fully connected layers on the challenging ImageNet. Extensive experiments verify the superiority of CoLR in comparison with some state-of-the-art models.http://dx.doi.org/10.1155/2019/7835797 |
| spellingShingle | Tan Guo Lei Zhang Xiaoheng Tan Liu Yang Zhiwei Guo Fupeng Wei CoLR: Classification-Oriented Local Representation for Image Recognition Complexity |
| title | CoLR: Classification-Oriented Local Representation for Image Recognition |
| title_full | CoLR: Classification-Oriented Local Representation for Image Recognition |
| title_fullStr | CoLR: Classification-Oriented Local Representation for Image Recognition |
| title_full_unstemmed | CoLR: Classification-Oriented Local Representation for Image Recognition |
| title_short | CoLR: Classification-Oriented Local Representation for Image Recognition |
| title_sort | colr classification oriented local representation for image recognition |
| url | http://dx.doi.org/10.1155/2019/7835797 |
| work_keys_str_mv | AT tanguo colrclassificationorientedlocalrepresentationforimagerecognition AT leizhang colrclassificationorientedlocalrepresentationforimagerecognition AT xiaohengtan colrclassificationorientedlocalrepresentationforimagerecognition AT liuyang colrclassificationorientedlocalrepresentationforimagerecognition AT zhiweiguo colrclassificationorientedlocalrepresentationforimagerecognition AT fupengwei colrclassificationorientedlocalrepresentationforimagerecognition |