PhD Project in Signature Learning for Object Detection Using Attention Mechanisms

Object detection traditionally relies on segmentation to extract features for recognition, but this can be challenging in cluttered or occluded environments. This project aims to develop a signature learning approach for detecting objects directly from data (e.g., images or videos) without explicit segmentation. By incorporating attention mechanisms, the model will focus on relevant regions and features that characterise the object of interest, enhancing detection accuracy.

This project will develop an attention-based model for object detection that learns distinct object signatures directly from unsegmented data. Traditional object recognition methods rely heavily on segmentation to isolate objects within images or videos, which can be challenging in cluttered or occluded environments. This project aims to bypass segmentation by leveraging attention mechanisms that focus on the most relevant regions and features, enabling the model to recognize objects based on their unique “signatures.”

The model will be trained on diverse datasets under varied conditions (e.g., different lighting, clutter levels, and occlusions) to enhance its robustness and adaptability. Through iterative refinement, the model’s attention mechanism will learn to identify key characteristics that distinguish objects, even in complex scenes. Its performance will be evaluated against traditional segmentation-based methods to demonstrate improvements in accuracy, efficiency, and adaptability.

Project Objectives:

[1] Develop an Attention-Based Model for Object Detection: Design and implement a model that uses attention mechanisms to detect objects directly from unsegmented data, without requiring explicit segmentation.

[2] Extend the Model to Learn Object Signatures: Enhance the model to identify unique object signatures, allowing it to capture distinctive features that characterize each object type.

[3] Optimise for Real-World Applications: Improve the model’s robustness and efficiency to handle real-world challenges, such as varied lighting, cluttered backgrounds, and occlusions.

Funding Information

To be eligible for consideration for a Home DfE or EPSRC Studentship (covering tuition fees and maintenance stipend of approx. £19,237 per annum), a candidate must satisfy all the eligibility criteria based on nationality, residency and academic qualifications.

To be classed as a Home student, candidates must meet the following criteria and the associated residency requirements:

• Be a UK National,
or • Have settled status,
or • Have pre-settled status,
or • Have indefinite leave to remain or enter the UK.

Candidates from ROI may also qualify for Home student funding.

Previous PhD study MAY make you ineligible to be considered for funding.

Please note that other terms and conditions also apply.

Please note that any available PhD studentships will be allocated on a competitive basis across a number of projects currently being advertised by the School.

A small number of international awards will be available for allocation across the School. An international award is not guaranteed to be available for this project, and competition across the School for these awards will be highly competitive.

Academic Requirements:

The minimum academic requirement for admission is normally an Upper Second Class Honours degree from a UK or ROI Higher Education provider in a relevant discipline, or an equivalent qualification acceptable to the University.

Entrance requirements

Graduate
The minimum academic requirement for admission to a research degree programme is normally an Upper Second Class Honours degree from a UK or ROI HE provider, or an equivalent qualification acceptable to the University. Further information can be obtained by contacting the School.

International Students

For information on international qualification equivalents, please check the specific information for your country.

English Language Requirements

Evidence of an IELTS* score of 6.0, with not less than 5.5 in any component or equivalent qualification acceptable to the University is required (*taken within the last 2 years).

International students wishing to apply to Queen’s University Belfast (and for whom English is not their first language), must be able to demonstrate their proficiency in English in order to benefit fully from their course of study or research. Non-EEA nationals must also satisfy UK Visas and Immigration (UKVI) immigration requirements for English language for visa purposes.

For more information on English Language requirements for EEA and non-EEA nationals see: www.qub.ac.uk/EnglishLanguageReqs.