Zhengzhe Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhengzhe Yang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Zhaohui Yuan
School of Information and Software Engineering, East China Jiaotong University, Nanchang 330013, China
2 shared publications Hao Ning
Department of Software Engineering,School of Software, East China Jiaotong University, Nanchang, China
1 shared publication- Hao Ning
School of Software, East China Jiaotong University, Nanchang 330013, China
1 shared publication Xiangyang Tang
Department of Software Engineering,School of Software, East China Jiaotong University, Nanchang, China
1 shared publication- Xiangyang Tang
School of Software, East China Jiaotong University, Nanchang 330013, China
1 shared publication
Latest Publications
- Open Access
- 30 May 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-16
Multiscale knowledge distillation with attention based fusion for robust human activity recognition
Knowledge distillation is an effective approach for training robust multi-modal machine learning models when synchronous multimodal data are unavailable. However, traditional knowledge distillation techniques have limitations in comprehensively transferring knowledge across modalities and models. This paper proposes a multiscale knowledge distillation framework to address these limitations. Specifically, we introduce a multiscale semantic graph mapping (SGM) loss function to enable more comprehensive knowledge transfer between teacher and student networks at multiple feature scales. We also design a fusion and tuning (FT) module to fully utilize correlations within and between different data types of the same modality when training teacher networks. Furthermore, we adopt transformer-based backbones to improve feature learning compared to traditional convolutional neural networks. We apply the proposed techniques to multimodal human activity recognition and compared with the baseline method, it improved by 2.31% and 0.29% on the MMAct and UTD-MHAD datasets. Ablation studies validate the necessity of each component.
- 30 May 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-16
Open AccessMultiscale knowledge distillation with attention based fusion for robust human activity recognition
Knowledge distillation is an effective approach for training robust multi-modal machine learning models when synchronous multimodal data are unavailable. However, traditional knowledge distillation techniques have limitations in comprehensively transferring knowledge across modalities and models. This paper proposes a multiscale knowledge distillation framework to address these limitations. Specifically, we introduce a multiscale semantic graph mapping (SGM) loss function to enable more comprehensive knowledge transfer between teacher and student networks at multiple feature scales. We also design a fusion and tuning (FT) module to fully utilize correlations within and between different data types of the same modality when training teacher networks. Furthermore, we adopt transformer-based backbones to improve feature learning compared to traditional convolutional neural networks. We apply the proposed techniques to multimodal human activity recognition and compared with the baseline method, it improved by 2.31% and 0.29% on the MMAct and UTD-MHAD datasets. Ablation studies validate the necessity of each component.
- Open Access
- 6 April 2024
- Published by MDPI AG in Electronics
- Vol. 13 (7) , 1388
GDCP-YOLO: Enhancing Steel Surface Defect Detection Using Lightweight Machine Learning Approach
Surface imperfections in steel materials potentially degrade quality and performance, thereby escalating the risk of accidents in engineering applications. Manual inspection, while traditional, is laborious and lacks consistency. However, recent advancements in machine learning and computer vision have paved the way for automated steel defect detection, yielding superior accuracy and efficiency. This paper introduces an innovative deep learning model, GDCP-YOLO, devised for multi-category steel defect detection. We enhance the reference YOLOv8n architecture by incorporating adaptive receptive fields via the DCNV2 module and channel attention in C2f. These integrations aim to concentrate on valuable features and minimize parameters. We incorporate the efficient Faster Block and employ Ghost convolutions to generate more feature maps with reduced computation. These modifications streamline feature extraction, curtail redundant information processing, and boost detection accuracy and speed. Comparative trials on the NEU-DET dataset underscore the state-of-the-art performance of GDCP-YOLO. Ablation studies and generalization experiments reveal consistent performance across a variety of defect types. The optimized lightweight architecture facilitates real-time automated inspection without sacrificing accuracy, offering invaluable insights to further deep learning techniques for surface defect identification across manufacturing sectors.
- 6 April 2024
- Published by MDPI AG in Electronics
- Vol. 13 (7) , 1388
Open AccessGDCP-YOLO: Enhancing Steel Surface Defect Detection Using Lightweight Machine Learning Approach
Surface imperfections in steel materials potentially degrade quality and performance, thereby escalating the risk of accidents in engineering applications. Manual inspection, while traditional, is laborious and lacks consistency. However, recent advancements in machine learning and computer vision have paved the way for automated steel defect detection, yielding superior accuracy and efficiency. This paper introduces an innovative deep learning model, GDCP-YOLO, devised for multi-category steel defect detection. We enhance the reference YOLOv8n architecture by incorporating adaptive receptive fields via the DCNV2 module and channel attention in C2f. These integrations aim to concentrate on valuable features and minimize parameters. We incorporate the efficient Faster Block and employ Ghost convolutions to generate more feature maps with reduced computation. These modifications streamline feature extraction, curtail redundant information processing, and boost detection accuracy and speed. Comparative trials on the NEU-DET dataset underscore the state-of-the-art performance of GDCP-YOLO. Ablation studies and generalization experiments reveal consistent performance across a variety of defect types. The optimized lightweight architecture facilitates real-time automated inspection without sacrificing accuracy, offering invaluable insights to further deep learning techniques for surface defect identification across manufacturing sectors.