Study level

  • PhD
  • Master of Philosophy
  • Honours

Faculty/School

Faculty of Engineering

School of Electrical Engineering and Robotics

Topic status

We're looking for students to study this topic.

Research centre

Supervisors

Professor Clinton Fookes
Position
Professor
Division / Faculty
Faculty of Engineering
Dr Kien Nguyen Thanh
Position
Senior Research Fellow
Division / Faculty
Faculty of Engineering
Professor Sridha Sridharan
Position
Principal Research Fellow
Division / Faculty
Faculty of Engineering

Overview

Recent advances in computer vision have demonstrated superhuman performance on a variety of visual tasks including image classification, object detection, human pose estimation and human analysis. However, current approaches for achieving these results center around models that purely learn from large-scale datasets with highly complex neural network architectures. Despite the impressive performance, pure data-driven models usually lack robustness, interpretability, and adherence to physical constraints or commonsense reasoning.

As in the real world, the visual world of computer vision is governed by specific physical laws. Incorporating physics knowledge into machine learning models has a great potential to improve the feasibility, plausibility of the outputs, to reduce the amount of training data required, and to train neural networks faster with better generalization and smaller training datasets.

This project will develop new methods to advance physics-informed machine learning.

Research activities

This project will develop new methods of physics-informed machine learning in different applications and domains. This will involve the development of new machine learning methods, and evaluating these on public datasets.

Research activities include:

  • research and development of novel physics-informed machine learning methods
  • experimental design
  • writing up, publishing and presenting research outcomes.

This project will build on an existing body of research conducted by the supervisory team.

Outcomes

For HDR students: the aim of the project is to develop new machine learning, computer vision and AI models to solve the research gaps in the related fields.

Skills and experience

You must have:

  • a strong math background
  • programming experience (preferably Python).

Some machine learning and/or computer vision experience is desired.

Scholarships

You may be eligible to apply for a research scholarship.

Explore our research scholarships

Keywords

Contact

Contact the supervisor for more information.