Yuanshun Cheng
Papers
1
Total Citations
9
H-Index
1
About
Dr. Yuanshun Cheng is a researcher specializing in deep learning applications for computer vision, with a particular focus on object detection in challenging underwater environments. His most-cited work, "Underwater Fish Object Detection based on Attention Mechanism improved Ghost-YOLOv5" (2022, 9 citations), addresses the critical challenge of deploying accurate yet computationally efficient detection models on resource-constrained robotic platforms. Dr. Cheng’s major contribution lies in enhancing the YOLOv5 architecture by integrating attention mechanisms and Ghost modules, significantly improving detection accuracy while reducing model complexity—a crucial advancement for real-time underwater monitoring. This work demonstrates his expertise in balancing model performance with practical deployability, a key concern in marine robotics and ecological surveillance. Though his citation count is still growing, Dr. Cheng’s research has immediate relevance for sustainable fisheries management and autonomous underwater vehicle navigation. His innovative approach to lightweight neural networks positions him as an emerging voice in applied deep learning, particularly for domain-specific challenges where computational resources are limited but accuracy cannot be compromised.
Research Focus
Key Achievements
Top Papers
- 1