Proceedings:
No. 3: AAAI-21 Technical Tracks 3
Volume
Issue:
Proceedings of the AAAI Conference on Artificial Intelligence, 35
Track:
AAAI Technical Track on Computer Vision II
Downloads:
Abstract:
Recent advances in unsupervised domain adaptation (UDA) show that transferable prototypical learning presents a powerful means for class conditional alignment, which encourages the closeness of cross-domain class centroids. However, the cross-domain inner-class compactness and the underlying fine-grained subtype structure remained largely underexplored. In this work, we propose to adaptively carry out the fine-grained subtype-aware alignment by explicitly enforcing the class-wise separation and subtype-wise compactness with intermediate pseudo labels. Our key insight is that the unlabeled subtypes of a class can be divergent to one another with different conditional and label shifts, while inheriting the local proximity within a subtype. The cases with or without the prior information on subtype numbers are investigated to discover the underlying subtype structure in an online fashion. The proposed subtype-aware dynamic UDA achieves promising results on a medical diagnosis task.
DOI:
10.1609/aaai.v35i3.16317
AAAI
Proceedings of the AAAI Conference on Artificial Intelligence, 35