Call for Papers

Domain Adaptation and Representation Transfer (DART)

13 October 2019 | Shenzhen, China

We would like to invite you to submit your papers for DART 2019 workshop to be held on the 13th of October 2019 in Shenzhen, China, as a satellite workshop of MICCAI.

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.

DART welcomes all contributions in the following areas:

● Meta learning

● Transfer learning

● Domain adaptation

● Invariant representations

● Learning from synthetic data

● Cross-task / multi-task learning

● Disentangling Representations

● Interpretable representations

● Learning from small data

● Unsupervised Learning

● Self-Supervised Learning

● X-shot learning

● Model distillation

● Auxiliary T asks

● Continual learning

The conference programme will include paper presentations, a poster session and keynote talks by prominent speakers in the field. All submitted papers will be reviewed by at least three PC members and handled by an Area Chair. Acceptance decisions will take into account paper novelty, technical depth, practical or theoretic impact.

Looking forward to your submissions,

Albarqouni, Shadi - Technical University Munich

Baust, Maximilian - NVIDIA / Technical University Munich

Cardoso, M. Jorge - King’s College London

Kamnitsas, Konstantinos - Imperial College London

Milletari, Fausto - NVIDIA

Quraini, Abood - NVIDIA

Rieke, Nicola - NVIDIA / Technical University Munich

Xu, Daguang - NVIDIA

Xu, Ziyue - NVIDIA