Feiyan He
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Feiyan He has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Cong Wang
School of Electronic and Information Engineering, Guangxi Normal University, Guilin 541004, China
1 shared publication - Haoran You
School of Electronic and Information Engineering, Guangxi Normal University, Guilin 541004, China
1 shared publication - Yunbai Qin
School of Electronic and Information Engineering, Guangxi Normal University, Guilin 541004, China
1 shared publication - Zhenjie Fan
School of Electronic and Information Engineering, Guangxi Normal University, Guilin 541004, P. R. China
1 shared publication - Zhonglan Lin
College of Electronics and Information Engineering, Shenzhen University, Shenzhen 518060, P. R. China
1 shared publication
Latest Publications
- 4 September 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Image and Graphics
Research on Scratch Defect Segmentation of Steel Surfaces Using MOSD-UNet Within a Semi-Supervised Self-Training Framework
To address the challenges of high annotation costs, class imbalance, and poor segmentation of small targets in steel scratch detection, we propose a semi-supervised self-training framework featuring Metal Object Scratch Detection U-Net (MOSD-UNet), a lightweight U-Net-based model. The framework initializes the model using limited labeled data and iteratively refines unlabeled data through high-confidence pseudo-labels, thereby reducing dependence on manual annotation. We designed a shallow feature-guided convolution module, termed Polarized Small Target Convolution (PST-Conv), which integrates the Channel Attention Module (CAM) and Gaussian Spatial Attention Module (GSAM) with a learnable Gaussian kernel to preserve fine-grained spatial features and mitigate information loss caused by pooling. Concurrently, we developed an efficient upsampling module called the Greatest Common Divisor Grouped Transposed Convolution (GCD-ConvT) module, which leverages grouped transposed convolution and channel compression to restore feature resolution while reducing parameters and enhancing inference speed. Finally, we introduce a specially designed mixed loss function that combines the Gradient Harmonizing Mechanism for Classification (GHM-C) and D[ ] loss, dynamically balancing the gradient distribution between easy and difficult samples and improving the structural consistency of segmented regions. All models, experimental configurations, and related code used in this study have been uploaded to the GitHub repository: https://github.com/Hayden-Mo/MOSD-UNet.git.
- 4 September 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Image and Graphics
Research on Scratch Defect Segmentation of Steel Surfaces Using MOSD-UNet Within a Semi-Supervised Self-Training Framework
To address the challenges of high annotation costs, class imbalance, and poor segmentation of small targets in steel scratch detection, we propose a semi-supervised self-training framework featuring Metal Object Scratch Detection U-Net (MOSD-UNet), a lightweight U-Net-based model. The framework initializes the model using limited labeled data and iteratively refines unlabeled data through high-confidence pseudo-labels, thereby reducing dependence on manual annotation. We designed a shallow feature-guided convolution module, termed Polarized Small Target Convolution (PST-Conv), which integrates the Channel Attention Module (CAM) and Gaussian Spatial Attention Module (GSAM) with a learnable Gaussian kernel to preserve fine-grained spatial features and mitigate information loss caused by pooling. Concurrently, we developed an efficient upsampling module called the Greatest Common Divisor Grouped Transposed Convolution (GCD-ConvT) module, which leverages grouped transposed convolution and channel compression to restore feature resolution while reducing parameters and enhancing inference speed. Finally, we introduce a specially designed mixed loss function that combines the Gradient Harmonizing Mechanism for Classification (GHM-C) and D[ ] loss, dynamically balancing the gradient distribution between easy and difficult samples and improving the structural consistency of segmented regions. All models, experimental configurations, and related code used in this study have been uploaded to the GitHub repository: https://github.com/Hayden-Mo/MOSD-UNet.git.