Junhua Zeng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Junhua Zeng has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Qibin Zhao
School of Automation, Guangdong University of Technology, Guangzhou, China
4 shared publications - Yuning Qiu
School of Automation, Guangdong University of Technology, Guangzhou, China
3 shared publications - Chao Li
Tensor Learning Team RIKEN Center for Advanced Intelligence Project (AIP) Japan
2 shared publications - Guoxu Zhou
School of Automation, Guangdong University of Technology, Guangzhou, China
2 shared publications - Andong Wang
School of Automation, Guangdong University of Technology, Guangzhou, China
1 shared publication - Heng-Chao Li
School of Information Science and Technology, Southwest Jiaotong University, Chengdu, China
1 shared publication
Latest Publications
- Open Access
SVDinsTN: A Tensor Network Paradigm for Efficient Structure Search from Regularized Modeling Perspective
Tensor network (TN) representation is a powerful technique for computer vision and machine learning. TN structure search (TN-SS) aims to search for a customized structure to achieve a compact representation, which is a challenging NP-hard problem. Recent "sampling-evaluation"-based methods require sampling an extensive collection of structures and evaluating them one by one, resulting in prohibitively high computational costs. To address this issue, we propose a novel TN paradigm, named SVD-inspired TN decomposition (SVDinsTN), which allows us to efficiently solve the TN-SS problem from a regularized modeling perspective, eliminating the repeated structure evaluations. To be specific, by inserting a diagonal factor for each edge of the fully-connected TN, SVDinsTN allows us to calculate TN cores and diagonal factors simultaneously, with the factor sparsity revealing a compact TN structure. In theory, we prove a convergence guarantee for the proposed method. Experimental results demonstrate that the proposed method achieves approximately 100 to 1000 times acceleration compared to the state-of-the-art TN-SS methods while maintaining a comparable level of representation ability.
Open AccessSVDinsTN: A Tensor Network Paradigm for Efficient Structure Search from Regularized Modeling Perspective
Tensor network (TN) representation is a powerful technique for computer vision and machine learning. TN structure search (TN-SS) aims to search for a customized structure to achieve a compact representation, which is a challenging NP-hard problem. Recent "sampling-evaluation"-based methods require sampling an extensive collection of structures and evaluating them one by one, resulting in prohibitively high computational costs. To address this issue, we propose a novel TN paradigm, named SVD-inspired TN decomposition (SVDinsTN), which allows us to efficiently solve the TN-SS problem from a regularized modeling perspective, eliminating the repeated structure evaluations. To be specific, by inserting a diagonal factor for each edge of the fully-connected TN, SVDinsTN allows us to calculate TN cores and diagonal factors simultaneously, with the factor sparsity revealing a compact TN structure. In theory, we prove a convergence guarantee for the proposed method. Experimental results demonstrate that the proposed method achieves approximately 100 to 1000 times acceleration compared to the state-of-the-art TN-SS methods while maintaining a comparable level of representation ability.
- 3 April 2024
- Published by Elsevier in Neural Networks
- Vol. 175, 106290
Bayesian tensor network structure search and its application to tensor completion
- 3 April 2024
- Published by Elsevier in Neural Networks
- Vol. 175, 106290
Bayesian tensor network structure search and its application to tensor completion
- Open Access
A Novel Tensor Ring Sparsity Measurement for Image Completion
As a promising data analysis technique, sparse modeling has gained widespread traction in the field of image processing, particularly for image recovery. The matrix rank, served as a measure of data sparsity, quantifies the sparsity within the Kronecker basis representation of a given piece of data in the matrix format. Nevertheless, in practical scenarios, much of the data are intrinsically multi-dimensional, and thus, using a matrix format for data representation will inevitably yield sub-optimal outcomes. Tensor decomposition (TD), as a high-order generalization of matrix decomposition, has been widely used to analyze multi-dimensional data. In a direct generalization to the matrix rank, low-rank tensor modeling has been developed for multi-dimensional data analysis and achieved great success. Despite its efficacy, the connection between TD rank and the sparsity of the tensor data is not direct. In this work, we introduce a novel tensor ring sparsity measurement (TRSM) for measuring the sparsity of the tensor. This metric relies on the tensor ring (TR) Kronecker basis representation of the tensor, providing a unified interpretation akin to matrix sparsity measurements, wherein the Kronecker basis serves as the foundational representation component. Moreover, TRSM can be efficiently computed by the product of the ranks of the mode-2 unfolded TR-cores. To enhance the practical performance of TRSM, the folded-concave penalty of the minimax concave penalty is introduced as a nonconvex relaxation. Lastly, we extend the TRSM to the tensor completion problem and use the alternating direction method of the multipliers scheme to solve it. Experiments on image and video data completion demonstrate the effectiveness of the proposed method.
Open AccessA Novel Tensor Ring Sparsity Measurement for Image Completion
As a promising data analysis technique, sparse modeling has gained widespread traction in the field of image processing, particularly for image recovery. The matrix rank, served as a measure of data sparsity, quantifies the sparsity within the Kronecker basis representation of a given piece of data in the matrix format. Nevertheless, in practical scenarios, much of the data are intrinsically multi-dimensional, and thus, using a matrix format for data representation will inevitably yield sub-optimal outcomes. Tensor decomposition (TD), as a high-order generalization of matrix decomposition, has been widely used to analyze multi-dimensional data. In a direct generalization to the matrix rank, low-rank tensor modeling has been developed for multi-dimensional data analysis and achieved great success. Despite its efficacy, the connection between TD rank and the sparsity of the tensor data is not direct. In this work, we introduce a novel tensor ring sparsity measurement (TRSM) for measuring the sparsity of the tensor. This metric relies on the tensor ring (TR) Kronecker basis representation of the tensor, providing a unified interpretation akin to matrix sparsity measurements, wherein the Kronecker basis serves as the foundational representation component. Moreover, TRSM can be efficiently computed by the product of the ranks of the mode-2 unfolded TR-cores. To enhance the practical performance of TRSM, the folded-concave penalty of the minimax concave penalty is introduced as a nonconvex relaxation. Lastly, we extend the TRSM to the tensor completion problem and use the alternating direction method of the multipliers scheme to solve it. Experiments on image and video data completion demonstrate the effectiveness of the proposed method.
- 15 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21 (1545598X) , 1-5
Hyperspectral and Multispectral Image Fusion via Bayesian Nonlocal CP Factorization
Recently, fusing low-resolution hyperspectral images (LR-HSIs) with high-resolution multispectral images (HR-MSIs) to obtain high-resolution HSI (HR-HSI) has become an emerging study. In this letter, Bayesian nonlocal canonical polyadic (CP) factorization (BNCPF) is proposed for fusing LR-HSI with HR-MSI, which applies CP factorization on the nonlocal tensors of HR-HSI. Compared with the vanilla scheme of applying CP factorization on HR-HSI, the nonlocal tensors reveal balanced low-rank properties along different modes, and thus CP factorization can better capture their intrinsic low-rankness. To avoid the immense CP-ranks selection on the nonlocal tensors, we develop a sparse Bayesian framework for automatic rank determination. For parameters estimation, we adopt the alternating direction method of multipliers (ADMMs) for the maximum a posteriori (MAP) estimator optimization. Experimental results verify the superiority and rank-robustness of the proposed method.
- 15 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21 (1545598X) , 1-5
Hyperspectral and Multispectral Image Fusion via Bayesian Nonlocal CP Factorization
Recently, fusing low-resolution hyperspectral images (LR-HSIs) with high-resolution multispectral images (HR-MSIs) to obtain high-resolution HSI (HR-HSI) has become an emerging study. In this letter, Bayesian nonlocal canonical polyadic (CP) factorization (BNCPF) is proposed for fusing LR-HSI with HR-MSI, which applies CP factorization on the nonlocal tensors of HR-HSI. Compared with the vanilla scheme of applying CP factorization on HR-HSI, the nonlocal tensors reveal balanced low-rank properties along different modes, and thus CP factorization can better capture their intrinsic low-rankness. To avoid the immense CP-ranks selection on the nonlocal tensors, we develop a sparse Bayesian framework for automatic rank determination. For parameters estimation, we adopt the alternating direction method of multipliers (ADMMs) for the maximum a posteriori (MAP) estimator optimization. Experimental results verify the superiority and rank-robustness of the proposed method.