Xiaoman Zhu

Foshan University

Papers

2

Total Citations

30

H-Index

2

About

Xiaoman Zhu is a researcher advancing the frontiers of computer vision and efficient deep learning, with a focus on semantic segmentation and robust visual localization. Their most influential work, "M-FasterSeg: An efficient semantic segmentation network based on neural architecture search" (2022, 19 citations), introduces a novel framework that leverages neural architecture search to design lightweight, high-performance segmentation models—a critical contribution for real-time applications in autonomous driving and robotics. Complementing this, Zhu’s study "Learning invariant semantic representation for long-term robust visual localization" (2022, 11 citations) tackles the persistent challenge of maintaining accurate localization across changing environmental conditions, such as varying lighting or seasons, by learning domain-invariant features. Together, these works demonstrate a commitment to bridging efficiency and robustness in visual perception systems. With a growing citation impact, Zhu’s research is shaping the development of practical, deployable AI solutions. Their achievements highlight a talent for translating complex theoretical concepts into tangible advancements, making them a rising voice in the field of efficient computer vision.

Research Focus

Key Achievements

2
H-Index
2
Papers
30
Total Citations
15
Avg Citations/Paper
🏆 Most Cited Paper
M-FasterSeg: An efficient semantic segmentation network based on neural architecture search
19 citations · 2022
📈 Most Prolific Year: 2022 (2 Papers)
🤝 Key Collaborators: 6
🏛 Institutions: Foshan University

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago