Inho Lim
Papers
1
Total Citations
3
H-Index
1
About
Inho Lim is a researcher advancing the frontier of 3D perception for autonomous systems, with a focus on domain adaptation and robust object detection. His work addresses a critical challenge: ensuring that deep learning models for 3D object detection—essential for autonomous driving and robotics—remain reliable when faced with real-world shifts in sensor data, such as sensor upgrades, weather variations, or geographic changes. In his highly cited 2024 paper, "Semi-Supervised Domain Adaptation Using Target-Oriented Domain Augmentation for 3D Object Detection," Lim introduces a novel semi-supervised framework that leverages target-oriented augmentation to bridge domain gaps without requiring extensive labeled data from new environments. This approach has already garnered attention (3 citations in its first year) for its practical impact on deploying detection systems across diverse conditions. Lim’s work is notable for its direct relevance to industry applications, offering a scalable solution to one of the most persistent bottlenecks in autonomous perception. By enabling models to adapt with minimal supervision, he is helping pave the way for safer, more resilient autonomous vehicles and robots in unpredictable, real-world settings.
Research Focus
Key Achievements
Top Papers
- 1