Jiafei Chen

Papers

Total Citations

H-Index

About

Jiafei Chen is a researcher whose work centers on efficient deep learning architectures for computer vision, with a particular emphasis on real-time semantic segmentation. His most-cited paper, "ELANet: an efficiently lightweight asymmetrical network for real-time semantic segmentation" (2024), addresses a critical bottleneck in deploying segmentation models for autonomous driving and robot navigation: the trade-off between accuracy and inference speed. Chen’s major contribution lies in designing asymmetrical network structures that dramatically reduce redundant parameters without sacrificing performance, enabling faster, more practical deployment on resource-constrained devices. This work has already garnered 4 citations in its first year, signaling growing recognition in the field. By tackling the dual challenges of oversized networks and excessive computational cost, Chen’s research directly impacts real-world applications where latency and efficiency are paramount—such as in self-driving cars and mobile robotics. His focus on lightweight architectures positions him at the forefront of efforts to bridge the gap between state-of-the-art accuracy and real-time feasibility, making his contributions highly relevant for students and researchers aiming to deploy vision models in edge computing scenarios.