Survey

Self-Supervised Learning and Its Applications in Medical Image Analysis

Siladittya Manna

Indian Statistical Institute, Kolkata, 20250 citations

Self-Supervised LearningMedical AIRepresentation Learning

Self-supervised learning (SSL) enables learning robust representations from unlabeled data and it consists of two stages: pretext and downstream. The representations learnt in the pretext task are transferred to the downstream task. Self-supervised learning has appli- cations in various domains, such as computer vision tasks, natural language processing, speech and audio processing, etc....