A Multi-View Fusion Method via Tensor Learning and Gradient Descent for Image Features
In many computer vision applications, one image can be represented by multiple heterogeneous features from different views, most of them commonly locate in high-dimensional space. These features can reflect different characteristics of one same object, they contain compatible and complementary infor...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9429214/ |
| _version_ | 1798001959238631424 |
|---|---|
| author | Laihang Yu Dongyan Zhang Ningzhong Liu Wengang Zhou |
| author_facet | Laihang Yu Dongyan Zhang Ningzhong Liu Wengang Zhou |
| author_sort | Laihang Yu |
| collection | DOAJ |
| description | In many computer vision applications, one image can be represented by multiple heterogeneous features from different views, most of them commonly locate in high-dimensional space. These features can reflect different characteristics of one same object, they contain compatible and complementary information among each other. How to construct an uniform low-dimensional embedding features which represent useful information of multi-view features is still an important and urgent issue to be solved. Therefore, we propose a multi-view fusion method via tensor learning and gradient descent (MvF-TG) in this paper. MvF-TG reconstructs a lowdimensional mapping subspace of each object by utilizing its k nearest neighbors, which preserves the underlying neighborhood structure of the original local manifold. The new method can effectively exploit the spatial correlation information from the multi-view features by tensor learning. Furthermore, the method constructs a gradient descent optimization model to generate the better unified low dimensional embedding. The proposed method is compared with several single-view and multi-view dimensional reduction methods in these indicators of P, R, MAP and F-measure. In the retrieval experiments, the P values of the newmethod respectively are 86.80%, 52.00%, 68.56% and 78.80% on datasets of Corel1k, Corel5k, Corel10k and Holidays. In the classification experiments, the mean accuracies of it respectively are 47.94% and 87.58% on datasets of Caltech101 and Coil. These values are higher than those obtained by other comparison methods, various evaluations based on the applications of image classification and retrieval demonstrates the effectiveness of our proposed method on multi-view feature fusion dimension reduction. |
| first_indexed | 2024-04-11T11:44:32Z |
| format | Article |
| id | doaj.art-7c60a68a2c7d4a70b87a0874cfbecd6c |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T11:44:32Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-7c60a68a2c7d4a70b87a0874cfbecd6c2022-12-22T04:25:39ZengIEEEIEEE Access2169-35362021-01-019793897939910.1109/ACCESS.2021.30794999429214A Multi-View Fusion Method via Tensor Learning and Gradient Descent for Image FeaturesLaihang Yu0https://orcid.org/0000-0001-7313-8914Dongyan Zhang1Ningzhong Liu2Wengang Zhou3School of Computer Science and Technology, Zhoukou Normal University, Zhoukou, ChinaCollege of Foreign Languages, Zhoukou Normal University, Zhoukou, ChinaDepartment of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaSchool of Computer Science and Technology, Zhoukou Normal University, Zhoukou, ChinaIn many computer vision applications, one image can be represented by multiple heterogeneous features from different views, most of them commonly locate in high-dimensional space. These features can reflect different characteristics of one same object, they contain compatible and complementary information among each other. How to construct an uniform low-dimensional embedding features which represent useful information of multi-view features is still an important and urgent issue to be solved. Therefore, we propose a multi-view fusion method via tensor learning and gradient descent (MvF-TG) in this paper. MvF-TG reconstructs a lowdimensional mapping subspace of each object by utilizing its k nearest neighbors, which preserves the underlying neighborhood structure of the original local manifold. The new method can effectively exploit the spatial correlation information from the multi-view features by tensor learning. Furthermore, the method constructs a gradient descent optimization model to generate the better unified low dimensional embedding. The proposed method is compared with several single-view and multi-view dimensional reduction methods in these indicators of P, R, MAP and F-measure. In the retrieval experiments, the P values of the newmethod respectively are 86.80%, 52.00%, 68.56% and 78.80% on datasets of Corel1k, Corel5k, Corel10k and Holidays. In the classification experiments, the mean accuracies of it respectively are 47.94% and 87.58% on datasets of Caltech101 and Coil. These values are higher than those obtained by other comparison methods, various evaluations based on the applications of image classification and retrieval demonstrates the effectiveness of our proposed method on multi-view feature fusion dimension reduction.https://ieeexplore.ieee.org/document/9429214/Multi-view fusion methodtensor learninggradient descentimage retrievalimage classification |
| spellingShingle | Laihang Yu Dongyan Zhang Ningzhong Liu Wengang Zhou A Multi-View Fusion Method via Tensor Learning and Gradient Descent for Image Features IEEE Access Multi-view fusion method tensor learning gradient descent image retrieval image classification |
| title | A Multi-View Fusion Method via Tensor Learning and Gradient Descent for Image Features |
| title_full | A Multi-View Fusion Method via Tensor Learning and Gradient Descent for Image Features |
| title_fullStr | A Multi-View Fusion Method via Tensor Learning and Gradient Descent for Image Features |
| title_full_unstemmed | A Multi-View Fusion Method via Tensor Learning and Gradient Descent for Image Features |
| title_short | A Multi-View Fusion Method via Tensor Learning and Gradient Descent for Image Features |
| title_sort | multi view fusion method via tensor learning and gradient descent for image features |
| topic | Multi-view fusion method tensor learning gradient descent image retrieval image classification |
| url | https://ieeexplore.ieee.org/document/9429214/ |
| work_keys_str_mv | AT laihangyu amultiviewfusionmethodviatensorlearningandgradientdescentforimagefeatures AT dongyanzhang amultiviewfusionmethodviatensorlearningandgradientdescentforimagefeatures AT ningzhongliu amultiviewfusionmethodviatensorlearningandgradientdescentforimagefeatures AT wengangzhou amultiviewfusionmethodviatensorlearningandgradientdescentforimagefeatures AT laihangyu multiviewfusionmethodviatensorlearningandgradientdescentforimagefeatures AT dongyanzhang multiviewfusionmethodviatensorlearningandgradientdescentforimagefeatures AT ningzhongliu multiviewfusionmethodviatensorlearningandgradientdescentforimagefeatures AT wengangzhou multiviewfusionmethodviatensorlearningandgradientdescentforimagefeatures |