Inyong Yun

Papers

Total Citations

229

H-Index

About

Inyong Yun is a leading researcher in computer vision, with a primary focus on real-time semantic segmentation for autonomous systems and robotics. His work addresses the critical challenge of balancing accuracy and inference speed in pixel-level prediction tasks—a tradeoff essential for deploying deep learning models in self-driving cars and intelligent robots. Yun is best known for introducing DABNet (Depth-wise Asymmetric Bottleneck), a groundbreaking architecture that achieves high-performance semantic segmentation with significantly reduced computational cost and parameters. His 2019 paper on DABNet has garnered 178 citations, reflecting its substantial impact on the field. Building on this success, Yun further advanced real-time urban scene understanding with his 2020 work on Depth-Wise Asymmetric Bottleneck with Point-Wise Aggregation Decoder, which has earned 51 citations. By designing efficient, lightweight neural networks that maintain accuracy while enabling rapid inference, Yun has made pivotal contributions to making deep learning practical for real-world autonomous applications. His research continues to influence the development of efficient vision systems for next-generation intelligent machines.