Keynote Speakers

Prof. Saman Halgamuge

The University of Melbourne, Australia

Special Title: Attention based Classification of Large Images with Small, Focussed Regions Highlighting the Differences
Abstract: We explore the use of Deep learning-based methods for classifying large images where the difference between images can only be observed in small number of pixels, for example, whole-slide images (WSIs) in cancer. Most current methods require extensive annotations at the sub-image (patch) level, which is time consuming. We recently proposed a new framework named annotation-efficient segmentation and attention-based classifier (ANSAC). ANSAC requires only slide-level labels to classify WSIs. ANSAC automatically segments regions relevant to classification, eliminating the need for extensive manual annotations focussed on small number of pixels.

Biodata: Prof Saman Halgamuge, Fellow of IEEE, IET, AAIA and NASSL received the B.Sc. Engineering degree in Electronics and Telecommunication from the University of Moratuwa, Sri Lanka, and the Dipl.-Ing and Ph.D. degrees in data engineering from the Technical University of Darmstadt, Germany. He is currently a Professor of the Department of Mechanical Engineering of the School of Electrical Mechanical and Infrastructure Engineering, The University of Melbourne and the visiting Deputy Vice Chancellor (Research and International) of SLIIT. He is listed as a top 2% most cited researcher for AI and Image Processing in the Stanford database. He was a distinguished Lecturer of IEEE Computational Intelligence Society (2018-21). He supervised 50 PhD students and 16 postdocs on AI and applications in Australia to completion. His research is funded by Australian Research Council, National Health and Medical Research Council, US DoD Biomedical Research program and international industry. His previous leadership roles include Head, School of Engineering at Australian National University and Associate Dean of the Engineering and IT Faculty of University of Melbourne. His publications can be viewed at




Speech Title: TBA
Abstract: TBA

Biodata: TBA


More speakers coming.