Pratibha Rathi

Papers

Total Citations

532

H-Index

About

Pratibha Rathi is a leading researcher in computer vision and deep learning, with a primary focus on efficient object detection and recognition systems. Her most impactful contribution is the development of the YOLO v3-Tiny model, a one-stage improved architecture that dramatically enhances both speed and accuracy in real-time object detection. This work, published in 2020, has garnered over 530 citations, reflecting its widespread adoption in applications ranging from pedestrian detection to autonomous systems. Rathi’s research addresses critical challenges in balancing computational efficiency with detection performance, making deep learning algorithms more accessible for resource-constrained environments. Her notable achievements include advancing the state-of-the-art in lightweight neural networks, enabling faster inference without sacrificing precision. Through her innovative approach to model optimization, Rathi has significantly influenced the trajectory of object detection research, providing practical solutions that bridge the gap between academic theory and real-world deployment. Her work continues to inspire new generations of researchers seeking to push the boundaries of efficient AI systems.