Thesis icon

Thesis

Learning with multimodal self-supervision

Abstract:

Deep learning has fueled an explosion of applications, yet training deep neural networks usually requires expensive human annotations. In this thesis we explore alternatives to avoid the substantial reliance on manual annotated examples when training deep neural networks. Specifically, we do so by either adapting self-supervised methods to automatically correct freely obtained data labels, or by completely abandoning the use of human labels and instead utilizing the natural co-occurrence o...

Expand abstract

Actions


Access Document


Files:

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
Oriel College
Role:
Author

Contributors

Role:
Supervisor
Role:
Supervisor
ORCID:
0000-0002-8945-8573
More from this funder
Name:
Engineering and Physical Sciences Research Council
Type of award:
DPhil
Level of award:
Doctoral
Awarding institution:
University of Oxford

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP