TADA: Taxonomy Adaptive Domain Adaptation

09/10/2021
by   Rui Gong, et al.
0

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.

READ FULL TEXT

page 9

page 15

research
12/22/2020

Open Set Domain Adaptation by Extreme Value Theory

Common domain adaptation techniques assume that the source domain and th...
research
04/01/2021

Divergence Optimization for Noisy Universal Domain Adaptation

Universal domain adaptation (UniDA) has been proposed to transfer knowle...
research
12/06/2022

Union-set Multi-source Model Adaptation for Semantic Segmentation

This paper solves a generalized version of the problem of multi-source m...
research
06/13/2023

Taxonomy-Structured Domain Adaptation

Domain adaptation aims to mitigate distribution shifts among different d...
research
06/25/2020

Automatic Domain Adaptation Outperforms Manual Domain Adaptation for Predicting Financial Outcomes

In this paper, we automatically create sentiment dictionaries for predic...
research
10/14/2020

Harnessing Uncertainty in Domain Adaptation for MRI Prostate Lesion Segmentation

The need for training data can impede the adoption of novel imaging moda...
research
07/27/2023

Taxonomy Adaptive Cross-Domain Adaptation in Medical Imaging via Optimization Trajectory Distillation

The success of automated medical image analysis depends on large-scale a...

Please sign up or login with your details

Forgot password? Click here to reset