Skip to main content

and
  1. No Access

    Chapter and Conference Paper

    TINC: Temporally Informed Non-contrastive Learning for Disease Progression Modeling in Retinal OCT Volumes

    Recent contrastive learning methods achieved state-of-the-art in low label regimes. However, the training requires large batch sizes and heavy augmentations to create multiple views of an image. With non-contr...

    Taha Emre, Arunava Chakravarty in Medical Image Computing and Computer Assis… (2022)