Domain Adaptation and Representation Transfer (DART)

News

DART 2020 was successfully held as a full-virtual online event. We thank the hundreds of attendees for their interest and inspiring discussions. Congratulations to Yang et al for winning the Best Paper Award!

Detailed schedule is decided: check the link.

Registration & Presentation: the registration is mandatory for one author, ideally the presenting author; we will be using the "pre-recorded presentation + online Q&A" for presentation, the deadline for submission of pre-recorded videos and posters (link sent via Email) is 12th September.

Workshop time: 8 October 2020, 9:00 - 18:00 UTC time

Important: camera-ready submission to new platform, guideline

NVIDIA sponsors a Titan RTX for the best paper award.

Paper submission deadline is extended to 07 July 2020 (11:59pm PST)

We are glad to announce that the 2nd MICCAI Workshop on Domain Adaptation and Representation Transfer (DART) has been accepted to be held in conjunction with the 23rd International Conference on Medical Image Computing and Computer Assisted Intervention!

Description

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 second MICCAI workshop on Domain Adaptation and Representation Transfer (DART) we aim to provide 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.