BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Some Machine Learning Technologies for Image processing and Beyond
   - Xiaohao Cai (University of Southampton)
DTSTART:20241129T120000Z
DTEND:20241129T130000Z
UID:TALK225208@talks.cam.ac.uk
CONTACT:Ferdia Sherry
DESCRIPTION:Machine/deep learning technologies have revolutionised many fi
 elds including computer vision and image processing. Their success general
 ly relies on big data. However\, for the data scarcity scenarios like in m
 edical imaging\, their performance could drop significantly. Moreover\, in
  many cases\, they also lack generalisation (e.g. the cross-domain adaptat
 ion problem) and explanation (e.g. explainable AI). In this presentation\,
  I will introduce some of our recent work on segmentation and classificati
 on targeting those challenges\, such as subspace feature representations f
 or few-shot learning\, multilevel explainable AI\, cross-domain adaptation
  in point clouds\, etc. 
LOCATION:MR12 Centre for Mathematical Sciences
END:VEVENT
END:VCALENDAR