I am looking for a PhD student for the 3-year project entitled “Semi-Supervised, Unsupervised, and Self-Supervised Transfer Learning for Computer Vision”.
Transfer learning has been demonstrated to improve the generalisation of deep neural networks to real-world applications, especially in situations where labelled training sets are missing. Current proposed methods work under certain conditions or tasks and, although a few universal approaches have been proposed, there are still several gaps, such as preventing negative transfer or catastrophic forgetting. The successful applicant will conduct research on transfer learning approaches, using partially labelled, or even unlabelled, datasets. The development of novel transfer learning approaches will be evaluated on real-world inter-disciplinary computer vision problems, such as plant and medical image analysis.
More information on how to apply is available at: https://www.jobs.ac.uk/job/CLV913/8-phd-studentships.
Deadline: 14th of January 2022