Yuexuan Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yuexuan Wang has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Di Yang
University of Florida, Department 4008, 1000 E. University Avenue, Gainesville, FL, United States [US
1 shared publication - Guo Cao
Nanjing University of Science and Technology
1 shared publication - Hongye Su
Zhejiang University
1 shared publication - Jian Chu
Shanghai Jiao Tong University
1 shared publication - Kun Huang
Department of Biostatistics and Health Data Science, Indiana University School of Medicine
1 shared publication - Lord Amoah
School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing, China
1 shared publication
Latest Publications
- Open Access
- 28 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 3091-3107
A Metareinforcement-Learning-Based Hyperspectral Image Classification With a Small Sample Set
The fine spectral information contained in hyperspectral images (HSI) is combined with rich spatial features to provide feature qualities that serve as distinguishing variables for efficient classification performance. The task's objective is to correctly identify and categorize several object categories in the HSI, such as the ground, flora, water, and buildings, based on their spectral characteristics beneficial for a variety of applications, including mapping minerals, analyzing vegetation, and mapping urban land-use. The difficulty of learning new task-specific knowledge from a limited data sample that encourages less training has not been overcome by deep learning models. The capacity of current models to generalize to new tasks on small data sets is still lacking. By learning features that are transferable to facilitate adaptation to novel tasks on small samples, meta-reinforcement learning shows promise in overcoming such difficulties. We proposed a meta-reinforcement learning (Meta-RL) model that decouples task inference to improve meta-training, and accelerate meta-learning with small HSI labeled samples for efficient classification. The model employs a Capsule network for effective cooperation between spectra-spatial bands. To minimize the temporal difference error, the Apex-X Deep Q network parameter update is used to meta-train our model. The proposed model obtains an overall accuracy between 95.85% and 96.78% with computational time between 3207.9s and 7487.9s for training and validation as well as between 21.57s and 32.98s for testing. The experimental results prove the competitiveness of the proposed model to existing traditional deep learning, meta-learning, and reinforcement learning methods in both classification accuracy and computational cost.
- 28 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 3091-3107
Open AccessA Metareinforcement-Learning-Based Hyperspectral Image Classification With a Small Sample Set
The fine spectral information contained in hyperspectral images (HSI) is combined with rich spatial features to provide feature qualities that serve as distinguishing variables for efficient classification performance. The task's objective is to correctly identify and categorize several object categories in the HSI, such as the ground, flora, water, and buildings, based on their spectral characteristics beneficial for a variety of applications, including mapping minerals, analyzing vegetation, and mapping urban land-use. The difficulty of learning new task-specific knowledge from a limited data sample that encourages less training has not been overcome by deep learning models. The capacity of current models to generalize to new tasks on small data sets is still lacking. By learning features that are transferable to facilitate adaptation to novel tasks on small samples, meta-reinforcement learning shows promise in overcoming such difficulties. We proposed a meta-reinforcement learning (Meta-RL) model that decouples task inference to improve meta-training, and accelerate meta-learning with small HSI labeled samples for efficient classification. The model employs a Capsule network for effective cooperation between spectra-spatial bands. To minimize the temporal difference error, the Apex-X Deep Q network parameter update is used to meta-train our model. The proposed model obtains an overall accuracy between 95.85% and 96.78% with computational time between 3207.9s and 7487.9s for training and validation as well as between 21.57s and 32.98s for testing. The experimental results prove the competitiveness of the proposed model to existing traditional deep learning, meta-learning, and reinforcement learning methods in both classification accuracy and computational cost.
- 9 November 2023
- Published by Springer Nature in Machine Intelligence Research
- Vol. 20 (6) , 909-922
Mask Distillation Network for Conjunctival Hyperemia Severity Classification
- 9 November 2023
- Published by Springer Nature in Machine Intelligence Research
- Vol. 20 (6) , 909-922
Mask Distillation Network for Conjunctival Hyperemia Severity Classification
- 1 January 2004
- Published by Elsevier in IFAC Proceedings Volumes
- Vol. 37 (1) , 743-748
Fuzzy Neural Network for Predicting 4-CBA Concentration of PTA Process
- 1 January 2004
- Published by Elsevier in IFAC Proceedings Volumes
- Vol. 37 (1) , 743-748
Fuzzy Neural Network for Predicting 4-CBA Concentration of PTA Process