Проф. др Синиша Тодоровић са Oregon State University одржаће предавање 16.09.2022. u 13:15 из области Computer vision у Сали 1

Електронског факултета.

У наставку је кратак садржај предавања и биографија предавача.

Abstract: This talk will be about few-shot instance segmentation in images -- a basic computer vision problem arising in many applications with access to only a few examples of target object classes due to, e.g., their rarity. Our main research accomplishments in this area will be presented, including: explicit modeling and discovery of latent object parts shared across object classes; data uncertainty map estimation for each instance segmentation and data uncertainty based regularization of our few-shot learning; and model uncertainty estimation with an efficient approximation based on the probit function. Our contributions produce statistically significant performance gains over the state of the art on the benchmark COCO dataset.

Speaker Bio:

Sinisa Todorovic is Professor in the School of Electrical Engineering and Computer Science at Oregon State University (OSU). He joined OSU in 2008, after three years of conducting postdoctoral research in the Beckman Institute at University of Illinois Urbana-Champaign (UIUC). He received his Ph.D. degree in electrical and computer engineering at University of Florida. Todorovic conducts research in computer vision with focus on object and human-activity recognition. He served as a co-Program Chair of IEEE International Conference on Automatic Face and Gesture Recognition FG 2015, and co-organized a number of tutorials and workshops on stochastic image grammars at top vision conferences. He has been Editor-in-Chief of the Image and Vision Computing journal since 2019.  His research has been funded by a number of US federal agencies, including NSF and DARPA, as well as the IT industry. He received Jack Neubauer Best Paper Award from IEEE Transactions on Vehicular Technology in 2014, and the Oregon State College of Engineering Research Collaboration Award in 2016. He is a co-founder and Chief Scientific Officer of Diffine LLC — a company which focuses on developing deep learning and other AI solutions for digital histopathology, drug optimization and discovery, and analysis of realistic living human tissues in vitro.