Papers
6
Total Citations
25
H-Index
3
About
Xilin Chen is a researcher whose work spans computer vision, medical image analysis, and robotic perception. A key contribution is **SurgNet** (2023, 10 citations), a self-supervised pretraining framework that leverages semantic consistency to achieve precise segmentation of blood vessels and surgical instruments in robot-assisted surgery—a critical step for autonomous navigation in the operating room. Chen also explores **class incremental learning** (2022, 6 citations), rethinking how models can learn new categories without forgetting old ones, and has advanced **3D instance segmentation** (2024, 2 citations) by transferring knowledge from synthetic scans to reduce reliance on costly labeled data. Earlier work includes **functionality discovery** (2020, 2 citations), enabling robots to predict how physical objects can be used for tasks like cutting, and foundational research in **blurred image restoration** (1997, 2 citations). With a career that bridges decades—from classical restoration to modern self-supervised learning—Chen’s work is shaping how machines see and interact with the world, particularly in high-stakes surgical settings where precision is paramount.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Pattern Recognition3 citations · 2016
- 4Functionality Discovery and Prediction of Physical Objects2 citations · 2020
- 5
- 6