Recent years have witnessed significant strides made by machine learning-based computer vision, thus enabling machines to interpret and understand visual information. However, most machine learning approaches exploit correlational relationships in a training data set to predict a target variable. When these correlations are spurious or unreliable, those methods often lack the ability to reason about the underlying causal relationships that govern visual phenomena. This PhD project aims to address this limitation by focusing on causal representation learning applicable to computer vision. The outcomes of this research will contribute to the growing field of causal reasoning/inference in computer vision.
About the project
The primary objective of this research is to develop novel techniques for learning causal representations from visual data. The entire project will be carried out in two steps. Firstly, we will investigate new deep architectures and algorithms that can capture and encode causal relationships present in visual data. These models should be able to infer the underlying causes behind observed visual patterns. Secondly, we will develop causal reasoning to facilitate various computer vision tasks, such as scene understanding, and action recognition.
For information and informal enquiries please contact: Prof. Jungong Han ([email protected] )
Prof. Jungong Han’s CV can be found at https://www.sheffield.ac.uk/dcs/people/academic/jungong-han
About the Department and Research Group
The student will work in the computer vision group within the department of computer science at the University of Sheffield.
99 percent of our research is rated in the highest two categories in the REF 2021, meaning it is classed as world-leading or internationally excellent.
- A minimum 2:1 undergraduate and/or postgraduate masters’ qualification (MSc) in a science and technology field: Computer Science, Engineering, Mathematics, with specialisation in Computer Vision, Machine Learning and AI
- Familiarity with machine learning and probabilistic models
- Relevant software knowledge and experience, for example Python and tensor frameworks (PyTorch or TensorFlow), C++, etc
- Excellent written and verbal communication skills
- The English language requirements must also be met. These can be found here: https://www.sheffield.ac.uk/postgraduate/english-language
How to apply
To apply for a PhD studentship, applications must be made directly to the University of Sheffield using the Postgraduate Online Application Form. Make sure you name Jungong Han as your proposed supervisor(s).
Information on what documents are required and a link to the application form can be found here – https://www.sheffield.ac.uk/postgraduate/phd/apply/applying
The form has comprehensive instructions for you to follow, and pop-up help is available.
This PhD studentship will cover standard UK home tuition fees and provide a tax-free stipend at the standard UK Research Council rate (currently £17,668 for
2022/23) for 3.5 years. If you are an overseas student, you are eligible to apply but you must have the means to pay the difference between the UK and overseas
tuition fees by securing additional funding or self-funding. Further information on International fees can be found here – https://www.sheffield.ac.uk/new-students/tuition-fees
View or Apply
To help us track our recruitment effort, please indicate in your cover/motivation letter where (globalvacancies.org) you saw this job posting.