Joseph Smith
PhD Student at Newcastle University | Deep Learning and Computer Vision Researcher
PhD Student at Newcastle University | Deep Learning and Computer Vision Researcher
I am currently pursuing my PhD at Newcastle University, where I research Image Formation and Digitisation Bias in Fine-Grained Classification Tasks. My work is conducted in collaboration with Procter & Gamble, focusing on how image capture and processing methods impact the performance of machine learning models in recognising subtle differences between similar classes.
My research interests lie at the intersection of deep learning, computer vision, and the challenges posed by real-world data. I am passionate about exploring innovative solutions to improve the accuracy and robustness of fine-grained image classification systems.
Outside of my academic work, I enjoy watching and following basketball, with a particular interest in the analytics side of the sport. I also find relaxation in listening to music, which helps me stay creative and inspired.
Newcastle University, Autumn 2021 - Present
Research Focuses: Image Formation and Digitisation Bias in Fine-Grained Classification Tasks, in collaboration with Procter & Gamble.
Newcastle University, Autumn 2018 - Summer 2021
Dissertation: Fine-Grained Image Classification Using Siamese Neural Networks and Detection of Unseen Classes
My undergraduate dissertation focused on developing a model using Siamese Neural Networks to improve fine-grained image classification, specifically addressing the challenge of detecting classes not present in the training set. This work laid the foundation for my ongoing research in my PhD programme.
Newcastle University, School of Computing, Autumn 2021 - Present
Served as a class demonstrator for both Bachelors and Masters degree modules, assisting students across a range of computer science courses. Responsibilities included helping students understand complex concepts, guiding them through practical exercises, and providing support during lab sessions.
C J Furey Construction, Summer 2020
Supported quantity surveyors in managing project costs, including cost estimation, financial reporting, and liaising with contractors and suppliers.
Barnett Waddingham LLP, Summer 2018 & 2019
Assisted with administrative tasks related to pension management, including data entry, document management, and customer service.
Authors: Zheming Zuo, Joseph Smith, Jonathan Stonehouse, Boguslaw Obara
Conference: European Conference on Computer Vision
Authors: Zheming Zuo, Joseph Smith, Jonathan Stonehouse, Boguslaw Obara
Conference: IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2024
Pages: 183--193
Authors: Joseph Smith, Zheming Zuo, Jonathan Stonehouse, Boguslaw Obara
Conference: International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2024
Pages: 448--457
Conference: CVPR Workshop on Fair, Data-Efficient, and Trusted Computer Vision
Location: Seattle Convention Centre, Seattle, USA
Date: Summer 2024
Conference: VISAPP
Location: Precise House Mantegna Roma, Rome, Italy
Date: Winter 2024