Learning with multimodal self-supervision

Thesis

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

Authors: Chen, H

• Type of award: DPhil
• Level of award: Doctoral
• Awarding institution: University of Oxford
• Language: English
• Keywords: convolutional neural network; self-supervision; multimodal; datasets
• Subjects: Deep learning (Machine learning); Computer vision