Collaborative Self-Regression Method With Nonlinear Feature Based on Multi-Task Learning for Image Classification
Multi-task learning has received great interest recently in the area of machine learning. It shows a considerable capacity to jointly learn multiple latent relationships hidden among tasks, and has been widely used in data mining and computer vision problems. In this paper, we propose a new multi-ta...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2018-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8424144/ |
| _version_ | 1818927809510244352 |
|---|---|
| author | Ao Li Zhiqiang Wu Huaiyin Lu Deyun Chen Guanglu Sun |
| author_facet | Ao Li Zhiqiang Wu Huaiyin Lu Deyun Chen Guanglu Sun |
| author_sort | Ao Li |
| collection | DOAJ |
| description | Multi-task learning has received great interest recently in the area of machine learning. It shows a considerable capacity to jointly learn multiple latent relationships hidden among tasks, and has been widely used in data mining and computer vision problems. In this paper, we propose a new multi-task based collaborative linear regression framework to address the image classification problem, which allows the class-specific and collaboratively shared latent structure components to be explored simultaneously. The proposed framework takes multi-target regression of each class as a task to transfer shared structures among them. To be more efficient and adaptive, the class-wise nonlinear subspace is also learned in this framework to earn inter-class discrimination and model adaptability. The proposed framework provides a unified and flexible perceptiveness for jointly learning the nonlinear projected features and regression parameters. Furthermore, a numerical scheme via iterative alternating optimization is also developed to solve the novel objective function in the proposed framework and guarantee the convergence. Extensive experimental results tested on several datasets demonstrated that our proposed framework outperforms existing competitive methods and achieves consistently high performance. |
| first_indexed | 2024-12-20T03:18:55Z |
| format | Article |
| id | doaj.art-79c1121a16e2494cbbb800c1c01fcc58 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T03:18:55Z |
| publishDate | 2018-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-79c1121a16e2494cbbb800c1c01fcc582022-12-21T19:55:16ZengIEEEIEEE Access2169-35362018-01-016435134352510.1109/ACCESS.2018.28621598424144Collaborative Self-Regression Method With Nonlinear Feature Based on Multi-Task Learning for Image ClassificationAo Li0https://orcid.org/0000-0003-0735-2917Zhiqiang Wu1Huaiyin Lu2Deyun Chen3Guanglu Sun4Postdoctoral Research Station of School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, ChinaDepartment of Electrical Engineering, Wright State University, Dayton, OH, USASchool of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, ChinaPostdoctoral Research Station of School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, ChinaPostdoctoral Research Station of School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, ChinaMulti-task learning has received great interest recently in the area of machine learning. It shows a considerable capacity to jointly learn multiple latent relationships hidden among tasks, and has been widely used in data mining and computer vision problems. In this paper, we propose a new multi-task based collaborative linear regression framework to address the image classification problem, which allows the class-specific and collaboratively shared latent structure components to be explored simultaneously. The proposed framework takes multi-target regression of each class as a task to transfer shared structures among them. To be more efficient and adaptive, the class-wise nonlinear subspace is also learned in this framework to earn inter-class discrimination and model adaptability. The proposed framework provides a unified and flexible perceptiveness for jointly learning the nonlinear projected features and regression parameters. Furthermore, a numerical scheme via iterative alternating optimization is also developed to solve the novel objective function in the proposed framework and guarantee the convergence. Extensive experimental results tested on several datasets demonstrated that our proposed framework outperforms existing competitive methods and achieves consistently high performance.https://ieeexplore.ieee.org/document/8424144/Linear regressionmulti-task learningimage classificationnonlinear featurenumerical optimization |
| spellingShingle | Ao Li Zhiqiang Wu Huaiyin Lu Deyun Chen Guanglu Sun Collaborative Self-Regression Method With Nonlinear Feature Based on Multi-Task Learning for Image Classification IEEE Access Linear regression multi-task learning image classification nonlinear feature numerical optimization |
| title | Collaborative Self-Regression Method With Nonlinear Feature Based on Multi-Task Learning for Image Classification |
| title_full | Collaborative Self-Regression Method With Nonlinear Feature Based on Multi-Task Learning for Image Classification |
| title_fullStr | Collaborative Self-Regression Method With Nonlinear Feature Based on Multi-Task Learning for Image Classification |
| title_full_unstemmed | Collaborative Self-Regression Method With Nonlinear Feature Based on Multi-Task Learning for Image Classification |
| title_short | Collaborative Self-Regression Method With Nonlinear Feature Based on Multi-Task Learning for Image Classification |
| title_sort | collaborative self regression method with nonlinear feature based on multi task learning for image classification |
| topic | Linear regression multi-task learning image classification nonlinear feature numerical optimization |
| url | https://ieeexplore.ieee.org/document/8424144/ |
| work_keys_str_mv | AT aoli collaborativeselfregressionmethodwithnonlinearfeaturebasedonmultitasklearningforimageclassification AT zhiqiangwu collaborativeselfregressionmethodwithnonlinearfeaturebasedonmultitasklearningforimageclassification AT huaiyinlu collaborativeselfregressionmethodwithnonlinearfeaturebasedonmultitasklearningforimageclassification AT deyunchen collaborativeselfregressionmethodwithnonlinearfeaturebasedonmultitasklearningforimageclassification AT guanglusun collaborativeselfregressionmethodwithnonlinearfeaturebasedonmultitasklearningforimageclassification |