Learning to Cluster under Domain Shift

Understand

While unsupervised domain adaptation methods based on deep architectures have achieved remarkable success in many computer vision tasks, they rely on a strong assumption, i.e.

• labeled source data must be available.
• In this work we overcome this assumption and we address the problem of transferring knowledge from a source to a target domain when both source and target data have no annotations.
• Inspired by recent works on deep clustering, our approach leverages information from data gathered from multiple source domains to build a domain-agnostic clustering model which is then refined at inference time when target data become available.