Towards diverse generation and reliable classification using neural networks

Thesis

Humans can easily understand their surroundings, analyze the situation, and even figure out the intentions of others, all in a few seconds. However, computers see the surroundings as an array of numbers and we need to write algorithms for them to make a sense of it. It is a huge challenge but significant strides have been made toward the scene understanding problem over the last decade, thanks to an increase in computing infrastructure and datasets. However, several challenges remain in ma...

Expand abstract

Authors: Kulharia, V

• DOI: 10.5287/bodleian:X57Ay22dZ
• Type of award: DPhil
• Level of award: Doctoral
• Awarding institution: University of Oxford
• Language: English
• Keywords: machine learning; generative adversarial networks; generative AI; deep learning; interactive video object segmentation; confidence calibration; weak-supervision; weakly-supervised image segmentation; computer vision; uncertainty
• Subjects: Computer vision; Deep learning (Machine learning)