Call for Papers
Domain Adaptation and Representation Transfer (DART)
September 2021 | Strasbourg, France
We would like to invite you to submit your papers for DART 2021 workshop to be held in October 1, 2021 in Strasbourg, France, 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 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.
DART welcomes all contributions in the following areas:
Transfer learning
Domain adaptation
Invariant representations
Fair, unbiased 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 Tasks
Continual learning
Meta 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 - Helmholtz AI / Technical University Munich
Cardoso, M. Jorge - King’s College London
Dou, Qi - Chinese University of Honk Kong
Kamnitsas, Konstantinos - Imperial College London
Rieke, Nicola - NVIDIA / Technical University Munich
Tsaftaris, Sotirios - University of Edinburgh
Xu, Daguang - NVIDIA
Xu, Ziyue - NVIDIA