Dingwen Wang
Papers
1
Total Citations
10
H-Index
1
About
Dingwen Wang is a researcher whose work bridges computer vision and remote sensing, with a particular focus on developing efficient deep learning models for resource-constrained environments. His key research areas include knowledge distillation, manifold learning, and scene classification for satellite and micro-robot applications. Wang's most cited work, "Knowledge Distillation of Grassmann Manifold Network for Remote Sensing Scene Classification" (2021, 10 citations), addresses a critical challenge: achieving high-performance image classification with small networks suitable for devices like satellites. By leveraging Grassmann manifold geometry, he pioneered a method that transfers knowledge from large, complex networks to compact ones without significant accuracy loss. This contribution is vital for real-world deployment where computational power and memory are limited. Wang's research demonstrates that sophisticated mathematical frameworks can be practically applied to make deep learning more accessible and efficient in edge computing scenarios, impacting the development of autonomous systems and space-based observation technologies.
Research Focus
Key Achievements
Top Papers
- 1