A Comprehensive Evaluation of Augmentations for Robust OOD Self-Supervised Contrastive Phonocardiogram Representation Learning

arXiv:2312.00502v2 Announce Type: replace
Abstract: Despite the recent increase in research activity, deep-learning models have not yet been widely accepted in several real-world settings, such as medicine. The shortage of high-quality annotated data often hinders the development of robust and generalizable models, which do not suffer from degraded effectiveness when presented with newly-collected, out-of-distribution (OOD) datasets. Contrastive Self-Supervised Learning (SSL) offers a potential solution to labeled data scarcity, as it takes advantage of unlabeled data to increase model effectiveness and …

abstract annotated data arxiv cs.lg cs.sd data development evaluation medicine q-bio.qm quality representation representation learning research robust shortage type world