Self-supervised and semi-supervised polyp segmentation using synthetic data

E Moreu, E Arazo, K McGuinness… - … Joint Conference on …, 2023 - ieeexplore.ieee.org
Early detection of colorectal polyps is of utmost importance for their treatment and for
colorectal cancer prevention. Computer vision techniques have the potential to aid …

Synthetic Balancing of Cardiac MRI Datasets

C Garcia-Cabrera, EA Sánchez, E Moreu… - Annual Conference on …, 2024 - Springer
Possessing a balanced dataset to train the segmentation models used in clinical products is
hugely important to enhance the performance in any given subset of patients. Due to …

Pinpoint Counterfactuals: Reducing social bias in foundation models via localized counterfactual generation

K Sirotkin, M Escudero-Viñolo, P Carballeira… - arxiv preprint arxiv …, 2024 - arxiv.org
Foundation models trained on web-scraped datasets propagate societal biases to
downstream tasks. While counterfactual generation enables bias analysis, existing methods …

Fashion CUT: Unsupervised domain adaptation for visual pattern classification in clothes using synthetic data and pseudo-labels

E Moreu, A Martinelli, M Naughton, P Kelly… - … Conference on Image …, 2023 - Springer
Accurate product information is critical for e-commerce stores to allow customers to browse,
filter, and search for products. Product data quality is affected by missing or incorrect …

Generalisable Cardiac MRI Analysis with Deep Learning

C Garcia Cabrera - 2024 - doras.dcu.ie
Cardiac Magnetic Resonance Imaging (CMR) is a powerful diagnostic tool for assessing
cardiac structure and function, providing detailed information crucial for clinical decision …

Semi-supervised Polyp Segmentation via a Dual-Teacher Student Framework

Q Lei, X Liu, W Luo, C Xu - International Conference on Ubiquitous …, 2024 - Springer
Automatic polyp segmentation is very critical for the early detection and treatment of colon
cancer. Most existing studies in polyp segmentation are devoted to using a fully supervised …