Shuai Feng

Papers

Total Citations

H-Index

About

Shuai Feng is a leading researcher in efficient computer vision, specializing in lightweight object detection and model compression. His work addresses the critical challenge of deploying high-performance detection systems on resource-constrained devices. Feng’s major contributions center on innovating the Single Shot MultiBox Detector (SSD) architecture to achieve remarkable efficiency without sacrificing accuracy. In his highly cited work, "L-SSD: lightweight SSD target detection based on depth-separable convolution" (2024, 23 citations), he pioneered the use of depth-separable convolutions to drastically reduce model parameters and computational cost, enabling real-time detection on edge devices. Building on this, his "SSD-KDGAN" (2024, 4 citations) introduced a novel framework combining knowledge distillation and generative adversarial networks, further compressing models while preserving detection fidelity. Feng’s research is pivotal for applications in autonomous driving, robotics, and mobile vision, where speed and low power consumption are paramount. His achievements demonstrate a rare ability to balance theoretical innovation with practical deployment, making him a key figure in the push toward accessible, high-performance AI.