After graduating with a Bachelor and Master’s degree in Computer Science and Engineering from the University of Dhaka, Bangladesh, I obtained my PhD degree from the Queensland University of Technology, Australia, supervised by Dr Feras Dayoub in September 2021.
My PhD research, titled “Performance Monitoring of Deep Learning Vision Systems During Deployment” delves into the vital realm of ensuring the reliability and accuracy of vision-based systems in mobile robotics. Through innovative techniques, I’ve tackled challenges in object detection and semantic segmentation performance monitoring. These contributions advance the state-of-the-art by enhancing our ability to monitor deep learning vision systems during deployment, without relying on ground truth labels. Explore these breakthroughs and more in my publications below.
- Quazi Marufur Rahman, Niko Sünderhauf, Peter Corke, and Feras Dayoub. “FSNet: A failure detection framework for semantic segmentation.” IEEE Robotics and Automation Letters 7, no. 2 (2022): 3030-3037.
- Quazi Marufur Rahman, Niko Sünderhauf, and Feras Dayoub. “Online Monitoring of Object Detection Performance During Deployment.” In 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4839-4845. IEEE, 2021.
- Quazi Marufur Rahman, Peter Corke, and Feras Dayoub. “Run-time monitoring of machine learning for robotic perception: A survey of emerging trends.” IEEE Access 9 (2021): 20067-20075.
- Quazi Marufur Rahman, Niko Sunderhauf, and Feras Dayoub. “Per-frame mAP prediction for continuous performance monitoring of object detection during deployment.” In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 152-160. 2021.
- Quazi Marufur Rahman, Niko Sünderhauf, and Feras Dayoub. “Did you miss the sign? A false negative alarm system for traffic sign detectors.” In 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3748-3753. IEEE, 2019.
Google scholar profile: Quazi Marufur Rahman