Haoran Huang
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
Haoran Huang has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Xiaochuan Luo
College of Information Science and Engineering, Northeastern University, Shenyang, China
2 shared publications - Chuhan Wu
Northeastern University
1 shared publication - Yulin Zhang
University of Picardie Jules Verne
1 shared publication
Latest Publications
- 3 November 2024
- Published by Springer Nature
- p. 51-65
CIMTD: Class Incremental Multi-Teacher Knowledge Distillation for Fractal Object Detection
- 3 November 2024
- Published by Springer Nature
- p. 51-65
CIMTD: Class Incremental Multi-Teacher Knowledge Distillation for Fractal Object Detection
- Open Access
A Holistic Approach to IGBT Board Surface Fractal Object Detection Based on the Multi-Head Model
In industrial visual inspection, foreign matters are mostly fractal objects. Detailed detection of fractal objects is difficult but necessary because better decision-making relies on more detailed and more comprehensive detection information. This presents a challenge for industrial applications. To solve this problem, we proposed a holistic approach to fractal object detection based on a multi-head model. We proposed the IWS (Information Watch and Study) module to provide enhancement learning capabilities for object information. It increases the detection dimension of the object and can perform more detailed detection. In order to realize the portability of the IWS module, it can be easily and quickly deployed to the existing advanced object detection model to achieve end-to-end detection. We proposed the FGI (Fine-Grained Information) Head, which is used to extract more comprehensive feature vectors from the original base model. We proposed the WST (Watch and Study Tactic) Learner for object information processing and adaptive learning of class cluster centers. Using the MRD (Multi-task Result Determination) strategy to combine the classification results and IWS results, the final detection results are derived. In the experiment, the IWS and MRD were mounted on three different models of the YOLO series. The experimental results show that YOLO+IWS has good foreign object detection capabilities to meet the needs of industrial visual inspection. Moreover, for the detailed detection ability of fractal objects, YOLO+IWS is better than the other 11 competing methods. We designed a new evaluation index and an adjustment mechanism of class learning weights to make better judgments and more balanced learning. Not only that, we applied YOLO+IWS to form a brand new object detection system.
Open AccessA Holistic Approach to IGBT Board Surface Fractal Object Detection Based on the Multi-Head Model
In industrial visual inspection, foreign matters are mostly fractal objects. Detailed detection of fractal objects is difficult but necessary because better decision-making relies on more detailed and more comprehensive detection information. This presents a challenge for industrial applications. To solve this problem, we proposed a holistic approach to fractal object detection based on a multi-head model. We proposed the IWS (Information Watch and Study) module to provide enhancement learning capabilities for object information. It increases the detection dimension of the object and can perform more detailed detection. In order to realize the portability of the IWS module, it can be easily and quickly deployed to the existing advanced object detection model to achieve end-to-end detection. We proposed the FGI (Fine-Grained Information) Head, which is used to extract more comprehensive feature vectors from the original base model. We proposed the WST (Watch and Study Tactic) Learner for object information processing and adaptive learning of class cluster centers. Using the MRD (Multi-task Result Determination) strategy to combine the classification results and IWS results, the final detection results are derived. In the experiment, the IWS and MRD were mounted on three different models of the YOLO series. The experimental results show that YOLO+IWS has good foreign object detection capabilities to meet the needs of industrial visual inspection. Moreover, for the detailed detection ability of fractal objects, YOLO+IWS is better than the other 11 competing methods. We designed a new evaluation index and an adjustment mechanism of class learning weights to make better judgments and more balanced learning. Not only that, we applied YOLO+IWS to form a brand new object detection system.