Help Privacy Policy Disclaimer
  Advanced SearchBrowse





TADA: Taxonomy Adaptive Domain Adaptation


Dai,  Dengxin
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society;

External Resource
No external resources are shared
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)

(Preprint), 22MB

Supplementary Material (public)
There is no public supplementary material available

Gong, R., Danelljan, M., Dai, D., Wang, W., Paudel, D. P., Chhatkuli, A., et al. (2021). TADA: Taxonomy Adaptive Domain Adaptation. Retrieved from https://arxiv.org/abs/2109.04813.

Cite as: https://hdl.handle.net/21.11116/0000-0009-89F0-D
Traditional domain adaptation addresses the task of adapting a model to a
novel target domain under limited or no additional supervision. While tackling
the input domain gap, the standard domain adaptation settings assume no domain
change in the output space. In semantic prediction tasks, different datasets
are often labeled according to different semantic taxonomies. In many
real-world settings, the target domain task requires a different taxonomy than
the one imposed by the source domain. We therefore introduce the more general
taxonomy adaptive domain adaptation (TADA) problem, allowing for inconsistent
taxonomies between the two domains. We further propose an approach that jointly
addresses the image-level and label-level domain adaptation. On the
label-level, we employ a bilateral mixed sampling strategy to augment the
target domain, and a relabelling method to unify and align the label spaces. We
address the image-level domain gap by proposing an uncertainty-rectified
contrastive learning method, leading to more domain-invariant and class
discriminative features. We extensively evaluate the effectiveness of our
framework under different TADA settings: open taxonomy, coarse-to-fine
taxonomy, and partially-overlapping taxonomy. Our framework outperforms
previous state-of-the-art by a large margin, while capable of adapting to
target taxonomies.