Dr. Ayaz Umer has worked in the field of visual attention prediction, focusing on developing innovative methods to enhance the performance and efficiency of saliency prediction networks. His research includes novel techniques to facilitate the development of saliency prediction networks with reduced computational cost by utilizing knowledge distillation. Furthermore, he has worked on Explainable AI (XAI) by providing an insight into how knowledge is transferred from the teacher to the student network under the knowledge distillation method.
From 2010 to 2014, he worked at COMSATS University, Attock Campus as a Research Associate and Lecturer, where he taught various undergraduate courses. From 2016 to 2019, he was with the University of South Australia, Adelaide, serving as a Course Coordinator, Practical Supervisor, and Tutor.
In August 2024, he joined the faculty of computer science and engineering at GIKI as an assistant professor. He is excited to both learn and teach cross-disciplinary.
Selected Publications
- Qiu, A., Aakyiir, M., Wang, R., Yang, Z., Umer, A., Lee, I., Hsu, H.Y. and Ma, J., 2020. Stretchable and calibratable graphene sensors for accurate strain measurement. Materials Advances, 1(2), pp.235-243.
- Umer, C. Termritthikun, T. Qiu, P. H. W. Leong and I. Lee, “On-Device Saliency Prediction Based on Pseudoknowledge Distillation,” in IEEE Transactions on Industrial Informatics, vol. 18, no. 9, pp. 6317-6325, Sept. 2022, doi: 10.1109/TII.2022.3153365.
- Termritthikun, C., Umer, A., Suwanwimolkul, S., Xia, F. and Lee, I., 2023. Explainable knowledge distillation for on-device chest x-ray classification. IEEE/ACM Transactions on Computational Biology and Bioinformatics.
- Termritthikun, C., Umer, A., Suwanwimolkul, S., Xia, F. and Lee, I., 2024. SalNAS: Efficient Saliency-prediction Neural Architecture Search with self-knowledge distillation. Engineering Applications of Artificial Intelligence, 136, p.109030.
