Papers
1
Total Citations
3
H-Index
1
About
Jongmin Yu is a researcher whose work lies at the intersection of computer vision and representation learning, with a particular focus on robust visual perception under adverse environmental conditions. His key research areas include image de-raining, disentangled representation learning, and domain adaptation for autonomous systems. Yu’s most notable contribution is his pioneering approach to handling rain-degraded imagery through disentangled representations, which allows neural networks to separate rain effects from underlying scene content—a critical capability for robot vision and autonomous driving. His paper "Learning to See in the Rain via Disentangled Representation" (2021) has garnered significant attention, accumulating over 3 citations and establishing a new paradigm for weather-robust visual analytics. Yu’s work directly addresses the vulnerability of deep neural networks to environmental noise, offering elegant solutions that improve performance without sacrificing interpretability. By advancing how machines perceive and reason in challenging conditions, Yu is shaping the future of reliable vision systems for real-world deployment.
Research Focus
Key Achievements
Top Papers
- 1Learning to See in the Rain via Disentangled Representation3 citations · 2021