Subhajit Choudhury
Papers
1
Total Citations
38
H-Index
1
About
Subhajit Choudhury is a researcher whose work lies at the intersection of computer vision, deep learning, and robotics, with a particular focus on bridging the gap between simulation and reality. His most cited paper, "Transfer Learning from Synthetic to Real Images Using Variational Autoencoders for Precise Position Detection" (2018, 38 citations), addresses a fundamental challenge in machine learning: the high cost of real-world data collection. By leveraging variational autoencoders, Choudhury demonstrated how models trained exclusively on synthetic images can be effectively transferred to real-world environments, achieving precise position detection without expensive manual labeling. This contribution has significant implications for robotics and autonomous systems, where labeled data is scarce. Choudhury’s work showcases a pragmatic approach to domain adaptation, making his research highly relevant for students and practitioners seeking efficient, scalable solutions in computer vision. His ability to combine theoretical rigor with practical applications marks him as an emerging voice in the field.
Research Focus
Key Achievements
Top Papers
- 1