Papers
1
Total Citations
1
H-Index
1
About
Yiyuan Ge is a rising researcher in computer vision and medical robotics, with a focus on advancing deep learning for surgical applications. Their key research areas include surgical instrument segmentation, semi-supervised learning, and transformer-based architectures for robotic surgery. Ge’s most notable contribution is the development of S4RoboFormer, a scribble-supervised surgical robotic segmentation transformer that leverages augmented consistency training to achieve high-performance segmentation with minimal labeled data. This work addresses a critical bottleneck in the field—the scarcity of large, annotated surgical datasets—by enabling effective learning from weak supervision. While still early in their career, Ge’s work has already garnered attention for its potential to improve the safety and efficacy of minimally invasive robotic surgeries. Their research stands out for its innovative combination of transformer models with consistency regularization, offering a practical solution to data scarcity in surgical AI. Ge’s contributions are particularly relevant for students and researchers interested in efficient deep learning for medical imaging and autonomous surgical systems.
Research Focus
Key Achievements
Top Papers
- 1