John Yang

Papers

Total Citations

H-Index

About

John Yang is a computer vision researcher whose work focuses on efficient deep learning architectures for real-world deployment. His most cited paper, "Depth Estimation with Simplified Transformer" (2022, 11 citations), tackles a critical challenge in the field: adapting the powerful Transformer architecture for latency-critical applications like autonomous driving and robotics. While Transformers have achieved state-of-the-art results across vision tasks, their computational demands often hinder practical use. Yang’s contribution lies in systematically simplifying the Transformer design for monocular depth estimation, demonstrating that competitive accuracy can be maintained with significantly reduced model complexity. This work addresses the growing need for efficient, deployable models in dense prediction tasks. His research sits at the intersection of computer vision, model efficiency, and practical deployment, making his findings valuable for both academic researchers and industry practitioners working on real-time perception systems. As the field increasingly prioritizes edge deployment, Yang’s focus on balancing performance with computational cost positions him as a contributor to the next generation of efficient vision models.