4 papers
Performance of Conformal Prediction in Capturing Aleatoric Uncertainty
Misgina Tsighe Hagos, Claes Lundström
Conformal prediction is a model-agnostic approach to generating prediction sets that cover the true class with a high probability. Although its prediction set size is expected to c…
Least-Ambiguous Multi-Label Classifier
Misgina Tsighe Hagos, Claes Lundström
Multi-label learning often requires identifying all relevant labels for training instances, but collecting full label annotations is costly and labor-intensive. In many datasets, o…
Validation of Conformal Prediction in Cervical Atypia Classification
Misgina Tsighe Hagos, Antti Suutala, Dmitrii Bychkov +6
Deep learning based cervical cancer classification can potentially increase access to screening in low-resource regions. However, deep learning models are often overconfident and d…
Rethinking Knee Osteoarthritis Severity Grading: A Few Shot Self-Supervised Contrastive Learning Approach
Niamh Belton, Misgina Tsighe Hagos, Aonghus Lawlor +1
Knee Osteoarthritis (OA) is a debilitating disease affecting over 250 million people worldwide. Currently, radiologists grade the severity of OA on an ordinal scale from zero to fo…