Low Complexity Models for Computer Vision Applications

About the Project

These projects are open to students worldwide, but have no funding attached. Therefore, the successful applicant will be expected to fund tuition fees at the relevant level (home or international) and any applicable additional research costs. Please consider this before applying.

Computer vision systems powered by deep learning are central to many modern applications, ranging from autonomous vehicles and medical imaging to industrial automation and precision agriculture. At the heart of these systems lies the image encoder, which transforms raw image data into compact representations for tasks such as classification and object detection. However, state-of-the-art encoders are often computationally intensive, demanding substantial energy and hardware resources for both training and deployment.

This project aims to develop lightweight image encoder architectures that support energy-efficient AI for computer vision, particularly in resource-constrained environments such as mobile devices and Internet of Things (IoT) systems. While current research has largely focused on maximizing performance through increasingly large models, it frequently overlooks the environmental and practical limitations of such approaches.

The proposed research will explore complexity reduction through intelligent image pre-processing. Many images contain large areas of redundant or semantically irrelevant data that contribute little to the task at hand. This project seeks to develop techniques for efficiently compressing images while preserving the semantically relevant information required for downstream tasks. The core hypothesis is that reducing input data enables the development of smaller, more efficient image encoders with minimal loss in accuracy.

The expected outcome is a set of compact, high-performing image encoders suitable for deployment in low-power environments. This work will also contribute to the advancement of sustainable AI systems, addressing the growing demand for environmentally responsible and accessible computer vision technologies.

Informal enquiries can be made by contacting Dr Korhonen (jari.korhonen@abdn.ac.uk)

Decisions will be based on academic merit. The successful applicant should have, or expect to obtain, a UK Honours Degree at 2.1 (or equivalent) in Computing Science. The topic requires basic knowledge of computer vision and deep learning, as well as practical experience on some computer vision and deep learning libraries and frameworks, e.g., OpenCV, PyTorch, TensorFlow, or JAX.

We encourage applications from all backgrounds and communities, and are committed to having a diverse, inclusive team.

Application Procedure:

Formal applications can be completed online: https://www.abdn.ac.uk/pgap/login.php.

You should apply for Degree of Doctor of Philosophy in Computing Science to ensure your application is passed to the correct team for processing.

Please clearly note the name of the lead supervisor and project titleon the application form. If you do not include these details, it may not be considered for the project.

Your application must include: A personal statement, an up-to-date copy of your academic CV, and clear copies of your educational certificates and transcripts.

Please note: you do not need to provide a research proposal with this application.

If you require any additional assistance in submitting your application or have any queries about the application process, please don't hesitate to contact us at researchadmissions@abdn.ac.uk

Funding Notes

This is a self-funding project open to students worldwide. Our typical start dates for this programme are February or October.

Fees for this programme can be found here Finance and Funding | Study Here | The University of Aberdeen