【讲座通知】On the Capacity of Face Representation

作者:发布时间:2019-04-23

时间:2019.4.25(周四)14:00    


地点:主楼八层报告厅   


主讲人:龚思雪  美国密歇根州立大学博士生        


主题:On the Capacity of Face Representation 


主讲人简介:Sixue Gong received her bachelor degree from Communication University of China in 2015. Since 2016, she has been working towards a Ph.D. degree in the Department of Computer Science and Engineering at Michigan State University. Her research interests include pattern recognition, image processing, and computer vision, with applications to face recognition.


讲座内容简介:Despite a significant progress in face recognition, a crucial question still remains unanswered: given a face representation, how many identities can it resolve? In other words, what is the capacity of the face representation? A scientific basis for estimating the capacity of a given face representation will not only benefit the evaluation and comparison of different representations, but will packing bounds on a low-dimensional manifold embedded within deep representation space. By explicitly accounting for the manifold structure of the representation as well two different sources of representational noise: epistemic (model) uncertainty and aleatoric (data) variability, our approach is able to estimate the capacity of any given face representation.