3rd MICCAI Workshop on

Domain Adaptation and Representation Transfer (DART)

Towards Learning Transferable, Interpretable, and Robust Representations

Best Paper Awards

Congratulations to:
-Best Paper: Nichuporuk et al, Cohort Bias Adaptation in Aggregated Datasets for Lesion Segmentation. - RTX 3090 awarded by NVIDIA
-Runner-Up: Kamnitsas et al, Transductive Image Segmentation: Self-Training and Effect of Uncertainty Estimation. - $300 award by Heartflow
-Honourable Mention: Ye et al, Unsupervised Domain Adaption via Similarity-based Prototypes for Cross-Modal Segmentation - $200 by Heartflow

News

Sponsoring awards for best works:
NVIDIA sponsors an RTX 3090 for the Best Paper Award.
HeartFlow sponsors monetary awards of $300 and $200 for the Best Paper Runner-Up and Honorable Mention works respectively.

** 5-day Deadline Extension for Paper Submissions**
==> 30th June, 23:59 PST <==

We are glad to announce that the 3rd MICCAI Workshop on Domain Adaptation and Representation Transfer (DART) will be held on Oct. 1 in conjunction with the 24rd 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 third MICCAI workshop on Domain Adaptation and Representation Transfer (DART) we aim to continue the 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.

Previous Workshops

DART2020, DART2019