Papers
1
Total Citations
4
H-Index
1
About
InKyu Shin is a rising researcher in computer vision and robotics, with a focus on test-time adaptation (TTA) and domain generalization. His work addresses a critical challenge in deploying deep recognition models in dynamic, real-world environments: the inability to pre-train on every possible visual scenario. Shin’s most cited paper, “Test-Time Adaptation in the Dynamic World With Compound Domain Knowledge Management” (2023), introduces a novel framework for lifelong model adaptation during deployment, enabling robots to continuously adjust to novel surroundings without retraining. This contribution has already garnered 4 citations, signaling early impact in the field. By managing compound domain shifts, Shin’s approach enhances model robustness and practical utility in autonomous systems. His research bridges the gap between static pre-training and dynamic deployment, offering scalable solutions for real-world AI. As a scholar committed to advancing adaptive intelligence, Shin’s work is poised to influence future developments in lifelong learning and robotic perception, making him a notable voice in the next generation of computer vision researchers.
Research Focus
Key Achievements
Top Papers
- 1