Huiyu Kuang
Papers
1
Total Citations
19
H-Index
1
About
Huiyu Kuang is a researcher specializing in efficient deep learning architectures for computer vision, with a particular focus on semantic segmentation and neural architecture search (NAS). Their most-cited work, "M-FasterSeg: An efficient semantic segmentation network based on neural architecture search" (2022), has garnered 19 citations, demonstrating its impact on the field. Kuang’s major contribution lies in designing lightweight, high-performance segmentation models that balance accuracy and computational efficiency—a critical challenge for real-time applications like autonomous driving and mobile robotics. By integrating NAS techniques, they have advanced automated model design, reducing reliance on manual engineering while achieving competitive results. This work not only enhances the practicality of semantic segmentation in resource-constrained environments but also inspires further exploration into NAS-driven optimization. Kuang’s research is notable for its emphasis on bridging algorithmic innovation with deployable solutions, making it highly relevant for students and researchers interested in efficient vision systems. Their contributions continue to influence the development of compact, accurate neural networks, solidifying their role in the evolving landscape of computer vision and automated machine learning.
Research Focus
Key Achievements
Top Papers
- 1