MICCAI Workshop on
Domain Adaptation and Representation Transfer (DART)
Towards Learning Transferable, Interpretable, and Robust Representations
Best Paper Award
Ilja Manakov from LMU, Germany
Our attendees @DART
More than 150 participants
We have 12 accepted papers, and the deadline for the camera-ready version is August 13. Thank you all for your submissions and we sincerely appreciate the time and effort from our reviewers. Looking forward to the discussions at DART!
We are very glad to announce that DART 2019 will be sponsored by Nvidia, who will offer a GPU for the Best Paper Award
Computer vision and medical imaging have been revolutionized by the introduction of advanced machine learning and deep learning methodologies. Recent approaches have shown unprecedented performance gains in tasks such as segmentation, classification, detection, and registration. Although these results (obtained mainly on public datasets) represent important milestones for the MICCAI community, most methods lack generalization capabilities when presented with previously unseen situations (corner cases) or different input data domains. This limits clinical applicability of these innovative approaches and therefore diminishes their impact. Transfer learning, representation learning and domain adaptation techniques have been used to tackle problems such as: model training using small datasets while obtaining generalizable representations; performing domain adaptation via few-shot learning; obtaining interpretable representations that are understood by humans; and leveraging knowledge learned from a particular domain to solve problems in another. Through the first MICCAI workshop on Domain Adaptation and Representation Transfer (DART) we aim to create a discussion forum to compare, evaluate and discuss methodological advancements and ideas that can improve the applicability of Machine Learning (ML) / Deep Learning (DL) approaches to clinical settings by making them robust and consistent across different domains.