講座時(shí)間：2023年11月28日10:00-11:00
講座地點(diǎn)：西土城校區(qū)教三136長(zhǎng)年報(bào)告廳
主 講 人：Josef Kittler教授
主 持 人：馬占宇 教授
Abstract:
Self-supervised learning is attracting a lot of attention in the research community because of its advantages over supervised learning in the context of building AI foundation models. These advantages include no cost of data annotation, avoidance of the negative impact of misleading information provided by coarse labels, the need for smaller training sets to facilitate learning, and the ability to model the data properties more directly. Self-supervised learning is accomplished by different pretext tasks, which are formulated in terms of appropriate objective functions. The learning methods themselves are based on a range of heuristics, such as distillation, temperature, asymmetry, batch normalisation, etc. The talk will discuss these heuristics by revisiting the problem of unsupervised learning based on the Gaussian mixture model estimation in the input data space. The parallel with clustering in the original space will motivate a novel approach for self-supervised learning in the embedding space. The merits of the proposed approach will be demonstrated on a range of experiments producing very promising results.
Bio:
Josef Kittler is Professor of Machine Intelligence at the Centre for Vision, Speech and Signal Processing, University of Surrey. He is also Distinguished Professor at the School of Artificial Intelligence and Computer Science, Jiangnan University. He received his BA, PhD and DSc degrees from the University of Cambridge. He teaches and conducts research in Machine Intelligence, with a focus on Biometrics, Video and Image Database retrieval, and Cognitive Vision. He published a Prentice Hall textbook on Pattern Recognition: A Statistical Approach, as well as more than 900 scientific papers, including circa 300 journal publications. He served as President of the International Association for Pattern Recognition in 1994-1996. Currently he serves on the Editorial Boards of Pattern Recognition, Pattern Recognition Letters and Springer Nature Computer Science. He was Series Editor of Springer Lecture Notes on Computer Science 2004-2016.
