3 citations · 5 across the 7 of their papers we have counts for
7 papers
Understanding and Mitigating Human-Labelling Errors in Supervised Contrastive Learning
Zijun Long, Lipeng Zhuang, George Killick +3
Human-annotated vision datasets inevitably contain a fraction of human mislabelled examples. While the detrimental effects of such mislabelling on supervised learning are well-rese…
CLCE: An Approach to Refining Cross-Entropy and Contrastive Learning for Optimized Learning Fusion
Zijun Long, George Killick, Lipeng Zhuang +3
State-of-the-art pre-trained image models predominantly adopt a two-stage approach: initial unsupervised pre-training on large-scale datasets followed by task-specific fine-tuning…
Foveation in the Era of Deep Learning
George Killick, Paul Henderson, Paul Siebert +1
In this paper, we tackle the challenge of actively attending to visual scenes using a foveated sensor. We introduce an end-to-end differentiable foveated active vision architecture…
Elucidating and Overcoming the Challenges of Label Noise in Supervised Contrastive Learning
Zijun Long, George Killick, Lipeng Zhuang +3
Image classification datasets exhibit a non-negligible fraction of mislabeled examples, often due to human error when one class superficially resembles another. This issue poses ch…
RoboLLM: Robotic Vision Tasks Grounded on Multimodal Large Language Models
Zijun Long, George Killick, Richard McCreadie +1
Robotic vision applications often necessitate a wide range of visual perception tasks, such as object detection, segmentation, and identification. While there have been substantial…
MultiWay-Adapater: Adapting large-scale multi-modal models for scalable image-text retrieval
Zijun Long, George Killick, Richard McCreadie +1
As Multimodal Large Language Models (MLLMs) grow in size, adapting them to specialized tasks becomes increasingly challenging due to high computational and memory demands. Indeed,…
When hard negative sampling meets supervised contrastive learning
Zijun Long, George Killick, Richard McCreadie +2
State-of-the-art image models predominantly follow a two-stage strategy: pre-training on large datasets and fine-tuning with cross-entropy loss. Many studies have shown that using…