Huaxiong Yao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Huaxiong Yao has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Renyi Chen
School of Electrical and Information Engineering, Tianjin University, Tianjin, China
3 shared publications - Hao Sun
Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, the School of Computer Science, and the National Language Resources Monitoring and Research Center for Network Media, Central China Normal University, Wuhan, China
2 shared publications - Wei Xie
Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, the School of Computer Science, and the National Language Resources Monitoring and Research Center for Network Media, Central China Normal University, Wuhan, China
2 shared publications - Xiaoqiang Lu
College of Physics and Information Engineering, Fuzhou University, Fuzhou, China
2 shared publications - Guirong Feng
College of Physics and Information Engineering Fuzhou University Fuzhou Fujian China
1 shared publication - Jia Guo
School of Computer, Central China Normal University, China
1 shared publication
Latest Publications
- 25 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-15
Class-Aware Consistency Learning for Open-Set Semi-Supervised Hyperspectral Image Classification
Semi-supervised hyperspectral image (HSI) classification methods focus on exploring the spectral and spatial information of unlabeled samples. However, existing methods generally follow the closed-set setting, assuming that unlabeled samples do not contain novel classes, which is hard to hold in practical applications. This paper aims to study semi-supervised HSI classification in the open-set setting, i.e., unlabeled samples fall into novel classes, and proposes a class-aware consistency learning (CACL) method. First, to explore discriminative spectral-spatial features, a position-aware transformer is developed, which effectively models spatial position priors between the center pixel and its neighboring pixels via a symmetric position-aware encoding. Then, to reduce the interference from novel class samples on the model’s discrimination, a prototype-driven consistency learning is proposed, which accurately selects unlabeled samples belonging to known classes via a known class sampler, and efficiently utilizes their spectral-spatial information by modeling consistent predictions across different views. Finally, to further improve the distinguishability between known classes, a prototype contrastive optimization is proposed to decrease the distance between samples from the same class and increase the distances between those from different classes in the feature domain. Furthermore, an adaptive segmentation threshold is designed to accurately predict known classes and reject novel classes. Extensive experiments verify that our CACL outperforms the state-of-the-art methods, achieving the overall accuracy of 81.65%, 88.61%, and 92.88% on the Indian Pines, Salinas, and Pavia University datasets, with 10 labeled samples in each known class. The code is available at https://github.com/rock-in/CACL-main.
- 25 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-15
Class-Aware Consistency Learning for Open-Set Semi-Supervised Hyperspectral Image Classification
Semi-supervised hyperspectral image (HSI) classification methods focus on exploring the spectral and spatial information of unlabeled samples. However, existing methods generally follow the closed-set setting, assuming that unlabeled samples do not contain novel classes, which is hard to hold in practical applications. This paper aims to study semi-supervised HSI classification in the open-set setting, i.e., unlabeled samples fall into novel classes, and proposes a class-aware consistency learning (CACL) method. First, to explore discriminative spectral-spatial features, a position-aware transformer is developed, which effectively models spatial position priors between the center pixel and its neighboring pixels via a symmetric position-aware encoding. Then, to reduce the interference from novel class samples on the model’s discrimination, a prototype-driven consistency learning is proposed, which accurately selects unlabeled samples belonging to known classes via a known class sampler, and efficiently utilizes their spectral-spatial information by modeling consistent predictions across different views. Finally, to further improve the distinguishability between known classes, a prototype contrastive optimization is proposed to decrease the distance between samples from the same class and increase the distances between those from different classes in the feature domain. Furthermore, an adaptive segmentation threshold is designed to accurately predict known classes and reject novel classes. Extensive experiments verify that our CACL outperforms the state-of-the-art methods, achieving the overall accuracy of 81.65%, 88.61%, and 92.88% on the Indian Pines, Salinas, and Pavia University datasets, with 10 labeled samples in each known class. The code is available at https://github.com/rock-in/CACL-main.
- 4 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21 (1545598X) , 1-5
Prototype-Based Pseudo-Label Refinement for Semi-Supervised Hyperspectral Image Classification
Pseudo-label learning-based methods usually regard class confidence above a certain threshold for unlabeled samples as pseudo-labels, which may result in pseudo-labels still containing wrong labels. In this letter, we propose a prototype-based pseudo-label refinement (PPLR) for semi-supervised hyperspectral image classification. The proposed PPLR filters wrong labels from pseudo-labels using class prototypes, which can improve the discrimination of the network. First, PPLR uses multi-head attentions to extract the spectral-spatial features, and designs an adaptive threshold that can be dynamically adjusted to generate high-confidence pseudo-labels. Then, PPLR constructs class prototypes for different categories using labeled sample features and unlabeled sample features with refined pseudo-labels to improve the quality of pseudo-labels by filtering wrong labels. Finally, PPLR further assigns reliable weights to these pseudo-labels in calculating their supervised loss, and introduces a center loss to improve the discrimination of features. When 10 labeled samples per category are utilized for training, PPLR achieves the overall accuracies of 82.11%, 86.70% and 92.50% on the Indian Pines, Houston2013 and Salinas datasets, respectively.
- 4 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21 (1545598X) , 1-5
Prototype-Based Pseudo-Label Refinement for Semi-Supervised Hyperspectral Image Classification
Pseudo-label learning-based methods usually regard class confidence above a certain threshold for unlabeled samples as pseudo-labels, which may result in pseudo-labels still containing wrong labels. In this letter, we propose a prototype-based pseudo-label refinement (PPLR) for semi-supervised hyperspectral image classification. The proposed PPLR filters wrong labels from pseudo-labels using class prototypes, which can improve the discrimination of the network. First, PPLR uses multi-head attentions to extract the spectral-spatial features, and designs an adaptive threshold that can be dynamically adjusted to generate high-confidence pseudo-labels. Then, PPLR constructs class prototypes for different categories using labeled sample features and unlabeled sample features with refined pseudo-labels to improve the quality of pseudo-labels by filtering wrong labels. Finally, PPLR further assigns reliable weights to these pseudo-labels in calculating their supervised loss, and introduces a center loss to improve the discrimination of features. When 10 labeled samples per category are utilized for training, PPLR achieves the overall accuracies of 82.11%, 86.70% and 92.50% on the Indian Pines, Houston2013 and Salinas datasets, respectively.
- Open Access
- 28 October 2022
- Published by Association for Computing Machinery (ACM)
- p. 442-448
PCKT: Problem Composition in Knowledge Tracking
With the rapid development of online education, personalized education becomes more and more important. The emergence of knowledge tracking (KT) has made a significant breakthrough in personalized education. In recent years, researchers have achieved some good results by building the KT model to search information and relationships between problems and skills. However, in reality, problems are sometimes similar. The skills may be exactly the same between two problems, but only the data is different. Therefore, it is extremely important to take this into account when making predictions. To address this problem, we construct a Problem Composition Knowledge Tracking Model (PCKT). In PCKT, problems are devided into corresponding data and skills, and connected by certain relation. Experiments demonstrated our PCKT achieved state-of-the-art results on two public datasets.
- 28 October 2022
- Published by Association for Computing Machinery (ACM)
- p. 442-448
Open AccessPCKT: Problem Composition in Knowledge Tracking
With the rapid development of online education, personalized education becomes more and more important. The emergence of knowledge tracking (KT) has made a significant breakthrough in personalized education. In recent years, researchers have achieved some good results by building the KT model to search information and relationships between problems and skills. However, in reality, problems are sometimes similar. The skills may be exactly the same between two problems, but only the data is different. Therefore, it is extremely important to take this into account when making predictions. To address this problem, we construct a Problem Composition Knowledge Tracking Model (PCKT). In PCKT, problems are devided into corresponding data and skills, and connected by certain relation. Experiments demonstrated our PCKT achieved state-of-the-art results on two public datasets.