Yuting Hong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yuting Hong has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Chengbin Peng
Ningbo University, Ningbo, China
4 shared publications Xiaojie Qiu
Zhejiang Cowain Automation Technology Company Ltd., Ningbo, China
3 shared publications- Diqun Yan
College of Digital Technology and Engineering, Ningbo University of Finance and Economics, Ningbo, China
2 shared publications - Hui Xiao
Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, China
2 shared publications - Li Dong
Ningbo University
2 shared publications Baochen Yao
1 shared publication
Latest Publications
- 6 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (4) , 4271-4284
Exploiting Minority Pseudo-Labels for Semi-Supervised Fine-Grained Road Scene Understanding
In fine-grained road scene understanding, semantic segmentation plays a crucial role in enabling vehicles to perceive and comprehend their surroundings. By assigning a specific class label to each pixel in an image, it allows for precise identification and localization of detailed road features, which is vital for high-quality scene understanding and downstream perception tasks. A key challenge in this domain lies in improving the recognition performance of minority classes while mitigating the dominance of majority classes, which is essential for achieving balanced and robust overall performance. However, traditional semi-supervised learning methods often train models overlooking the imbalance between classes. To address this issue, firstly, we propose a general training module that learns from all the pseudo-labels without a conventional filtering strategy. Secondly, we propose a professional training module to learn specifically from reliable minority-class pseudo-labels identified by a novel mismatch score metric. The two modules are crossly supervised by each other so that it reduces model coupling which is essential for semi-supervised learning. During contrastive learning, to avoid the dominance of the majority classes in the feature space, we propose a strategy to assign evenly distributed anchors for different classes in the feature space. Experimental results on multiple public benchmarks show that our method surpasses traditional approaches in recognizing tail classes.
- 6 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (4) , 4271-4284
Exploiting Minority Pseudo-Labels for Semi-Supervised Fine-Grained Road Scene Understanding
In fine-grained road scene understanding, semantic segmentation plays a crucial role in enabling vehicles to perceive and comprehend their surroundings. By assigning a specific class label to each pixel in an image, it allows for precise identification and localization of detailed road features, which is vital for high-quality scene understanding and downstream perception tasks. A key challenge in this domain lies in improving the recognition performance of minority classes while mitigating the dominance of majority classes, which is essential for achieving balanced and robust overall performance. However, traditional semi-supervised learning methods often train models overlooking the imbalance between classes. To address this issue, firstly, we propose a general training module that learns from all the pseudo-labels without a conventional filtering strategy. Secondly, we propose a professional training module to learn specifically from reliable minority-class pseudo-labels identified by a novel mismatch score metric. The two modules are crossly supervised by each other so that it reduces model coupling which is essential for semi-supervised learning. During contrastive learning, to avoid the dominance of the majority classes in the feature space, we propose a strategy to assign evenly distributed anchors for different classes in the feature space. Experimental results on multiple public benchmarks show that our method surpasses traditional approaches in recognizing tail classes.
- 25 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21 (1545598X) , 1-5
C²F²: Cross-Task Cross-Domain Feature Fusion for Semi-Supervised Change Detection
Semi-supervised learning for change detection (CD), which significantly reduces the labor costs associated with data annotation, has recently garnered substantial attention. In this study, we propose to enhance traditional semi-supervised learning frameworks by leveraging cross-task cross-domain (CTCD) models, which generate complementary features that differ from standard hidden features. The procedure is as follows. Firstly, the standard features obtained from a traditional encoding-decoding structure are fused with attention-augmented complementary features. Secondly, a secondary decoder maps the fused heterogeneous features into the label space to obtain high-quality pseudo-labels, offering more precise guidance for semi-supervised learning on traditional structures. This approach improves pseudo-labels by leveraging the strength of CTCD models, including large pre-trained models, to enhance the semi-supervised learning process of domain-specific and task-specific models. Experimental results on benchmark datasets demonstrate that our proposed approach surpasses state-of-the-art methods.
- 25 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21 (1545598X) , 1-5
C²F²: Cross-Task Cross-Domain Feature Fusion for Semi-Supervised Change Detection
Semi-supervised learning for change detection (CD), which significantly reduces the labor costs associated with data annotation, has recently garnered substantial attention. In this study, we propose to enhance traditional semi-supervised learning frameworks by leveraging cross-task cross-domain (CTCD) models, which generate complementary features that differ from standard hidden features. The procedure is as follows. Firstly, the standard features obtained from a traditional encoding-decoding structure are fused with attention-augmented complementary features. Secondly, a secondary decoder maps the fused heterogeneous features into the label space to obtain high-quality pseudo-labels, offering more precise guidance for semi-supervised learning on traditional structures. This approach improves pseudo-labels by leveraging the strength of CTCD models, including large pre-trained models, to enhance the semi-supervised learning process of domain-specific and task-specific models. Experimental results on benchmark datasets demonstrate that our proposed approach surpasses state-of-the-art methods.
- 10 July 2024
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 136
A multi-view consistency framework with semi-supervised domain adaptation
- 10 July 2024
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 136
A multi-view consistency framework with semi-supervised domain adaptation
- 7 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 8077-8087
Multi-Level Label Correction by Distilling Proximate Patterns for Semi-Supervised Semantic Segmentation
Semi-supervised semantic segmentation relieves the reliance on large-scale labeled data by leveraging unlabeled data. Recent semi-supervised semantic segmentation approaches mainly resort to pseudo-labeling methods to exploit unlabeled data. However, unreliable pseudo-labeling can undermine the semi-supervision processes. In this paper, we propose an algorithm called Multi-Level Label Correction (MLLC), which aims to use graph neural networks to capture structural relationships in Semantic-Level Graphs (SLGs) and Class-Level Graphs (CLGs) to rectify erroneous pseudo-labels. Specifically, SLGs represent semantic affinities between pairs of pixel features, and CLGs describe classification consistencies between pairs of pixel labels. With the support of proximate pattern information from graphs, MLLC can rectify incorrectly predicted pseudo-labels and can facilitate discriminative feature representations. We design an end-to-end network to train and perform this effective label corrections mechanism. Experiments demonstrate that MLLC can significantly improve supervised baselines and outperforms state-of-the-art approaches in different scenarios on Cityscapes and PASCAL VOC 2012 datasets. Specifically, MLLC improves the supervised baseline by at least 5% and 2% with DeepLabV2 and DeepLabV3+ respectively under different partition protocols.
- 7 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 8077-8087
Multi-Level Label Correction by Distilling Proximate Patterns for Semi-Supervised Semantic Segmentation
Semi-supervised semantic segmentation relieves the reliance on large-scale labeled data by leveraging unlabeled data. Recent semi-supervised semantic segmentation approaches mainly resort to pseudo-labeling methods to exploit unlabeled data. However, unreliable pseudo-labeling can undermine the semi-supervision processes. In this paper, we propose an algorithm called Multi-Level Label Correction (MLLC), which aims to use graph neural networks to capture structural relationships in Semantic-Level Graphs (SLGs) and Class-Level Graphs (CLGs) to rectify erroneous pseudo-labels. Specifically, SLGs represent semantic affinities between pairs of pixel features, and CLGs describe classification consistencies between pairs of pixel labels. With the support of proximate pattern information from graphs, MLLC can rectify incorrectly predicted pseudo-labels and can facilitate discriminative feature representations. We design an end-to-end network to train and perform this effective label corrections mechanism. Experiments demonstrate that MLLC can significantly improve supervised baselines and outperforms state-of-the-art approaches in different scenarios on Cityscapes and PASCAL VOC 2012 datasets. Specifically, MLLC improves the supervised baseline by at least 5% and 2% with DeepLabV2 and DeepLabV3+ respectively under different partition protocols.
- Open Access
- 23 October 2021
- Published by Association for Computing Machinery (ACM)
- p. 2040-2043
Application Research of Asset Allocation Model in Performance Analysis of China's Oil Industry
In this paper, factor analysis is used to analyze the performance of listed companies in China's oil industry. The research shows that the performance of oil companies can be evaluated from four aspects: solvency, growth, management and profitability, and solvency is particularly important. Then according to the performance of listed companies in the oil industry, this paper analyzes the application of asset allocation model in the performance of listed companies in China's oil industry and finds that: MV model is more suitable for the asset allocation in China's oil industry, and the asset allocation strategy with variable mean and variance can overcome the simple EW (or SW) strategy.
- 23 October 2021
- Published by Association for Computing Machinery (ACM)
- p. 2040-2043
Open AccessApplication Research of Asset Allocation Model in Performance Analysis of China's Oil Industry
In this paper, factor analysis is used to analyze the performance of listed companies in China's oil industry. The research shows that the performance of oil companies can be evaluated from four aspects: solvency, growth, management and profitability, and solvency is particularly important. Then according to the performance of listed companies in the oil industry, this paper analyzes the application of asset allocation model in the performance of listed companies in China's oil industry and finds that: MV model is more suitable for the asset allocation in China's oil industry, and the asset allocation strategy with variable mean and variance can overcome the simple EW (or SW) strategy.