TADA: Taxonomy Adaptive Domain Adaptation

by   Rui Gong, et al.

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 new target domain taxonomies.



There are no comments yet.


page 9

page 15


Open Set Domain Adaptation by Extreme Value Theory

Common domain adaptation techniques assume that the source domain and th...

Divergence Optimization for Noisy Universal Domain Adaptation

Universal domain adaptation (UniDA) has been proposed to transfer knowle...

Open Set Domain Adaptation for Image and Action Recognition

Since annotating and curating large datasets is very expensive, there is...

Unveiling Class-Labeling Structure for Universal Domain Adaptation

As a more practical setting for unsupervised domain adaptation, Universa...

Automatic Domain Adaptation Outperforms Manual Domain Adaptation for Predicting Financial Outcomes

In this paper, we automatically create sentiment dictionaries for predic...

Harnessing Uncertainty in Domain Adaptation for MRI Prostate Lesion Segmentation

The need for training data can impede the adoption of novel imaging moda...

Target contrastive pessimistic risk for robust domain adaptation

In domain adaptation, classifiers with information from a source domain ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.