Wenhang Xu

Papers

Total Citations

H-Index

About

Wenhang Xu is a researcher at the forefront of efficient deep learning for computer vision, with a particular focus on semantic segmentation for Internet of Things (IoT) applications. His work addresses the critical challenge of balancing high accuracy with computational efficiency, enabling advanced visual perception in resource-constrained environments like industrial robotics and autonomous driving. Xu’s most influential contribution, the MIFNet (Multiscale Information Fusion Network), introduced a lightweight architecture that achieves competitive segmentation performance while significantly reducing model complexity. This paper, published in 2021, has garnered 29 citations, reflecting its impact on the development of practical, deployable vision systems. By pioneering methods that fuse multiscale features without excessive computational overhead, Xu has helped bridge the gap between state-of-the-art deep learning and real-world IoT deployment. His research is particularly valuable for students and engineers seeking to understand how to design efficient neural networks that maintain robustness across diverse scales and contexts. Xu’s work continues to inspire further innovations in lightweight, high-performance visual intelligence.