Timezone: »

Universal Domain Adaptation through Self Supervision
Kuniaki Saito · Donghyun Kim · Stan Sclaroff · Kate Saenko

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #1007

Unsupervised domain adaptation methods traditionally assume that all source categories are present in the target domain. In practice, little may be known about the category overlap between the two domains. While some methods address target settings with either partial or open-set categories, they assume that the particular setting is known a priori. We propose a more universally applicable domain adaptation approach that can handle arbitrary category shift, called Domain Adaptative Neighborhood Clustering via Entropy optimization (DANCE). Our approach combines two novel ideas: First, as we cannot fully rely on source categories to learn features discriminative for the target, we propose a novel neighborhood clustering technique to learn the structure of the target domain in a self-supervised way. Second, we use entropy-based feature alignment and rejection to align target features with the source, or reject them as unknown categories based on their entropy. We show through extensive experiments that DANCE outperforms baselines across open-set, open-partial and partial domain adaptation settings.

Author Information

Kuniaki Saito (Boston University)
Donghyun Kim (Boston University)
Stan Sclaroff (Boston University)
Kate Saenko (Boston University & MIT-IBM Watson AI Lab, IBM Research)

More from the Same Authors