Research Fellow · Computer Vision & Deep Learning
Alzayat Saleh
James Cook University, Australia
I build computer vision systems that work outside the lab: in murky water, in bright paddocks and in clinical scans. Much of my work asks how to train reliable models when labelled data is scarce, using self-supervised, semi-supervised and weakly supervised learning, and how to make those models small and fast enough to deploy on real equipment.
Research
Across all of it
Learning with few labels (self-, semi- and weakly supervised), realistic benchmark datasets, and lightweight networks for deployment in the field.
Publications
Loading publications…
Contact
I am open to collaborations in computer vision for ecology, aquaculture, agriculture and robotics.