DeepAI AI Chat
Log In Sign Up

Butterfly: A Panacea for All Difficulties in Wildly Unsupervised Domain Adaptation

by   Feng Liu, et al.
University of Technology Sydney
The University of Tokyo

In unsupervised domain adaptation (UDA), classifiers for the target domain (TD) are trained with clean labeled data from the source domain (SD) and unlabeled data from TD. However, in the wild, it is hard to acquire a large amount of perfectly clean labeled data in SD given limited budget. Hence, we consider a new, more realistic and more challenging problem setting, where classifiers have to be trained with noisy labeled data from SD and unlabeled data from TD---we name it wildly UDA (WUDA). We show that WUDA provably ruins all UDA methods if taking no care of label noise in SD, and to this end, we propose a Butterfly framework, a panacea for all difficulties in WUDA. Butterfly maintains four models (e.g., deep networks) simultaneously, where two take care of all adaptations (i.e., noisy-to-clean, labeled-to-unlabeled, and SD-to-TD-distributional) and then the other two can focus on classification in TD. As a consequence, Butterfly possesses all the necessary components for all the challenges in WUDA. Experiments demonstrate that under WUDA, Butterfly significantly outperforms existing baseline methods.


page 8

page 9

page 16


Butterfly: Robust One-step Approach towards Wildly-unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) trains with clean labeled data in s...

Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis

Deep learning based medical image diagnosis has shown great potential in...

Rethinking Unsupervised Domain Adaptation for Semantic Segmentation

Unsupervised domain adaptation (UDA) adapts a model trained on one domai...

Domain-Irrelevant Representation Learning for Unsupervised Domain Generalization

Domain generalization (DG) aims to help models trained on a set of sourc...

TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation

In few-shot domain adaptation (FDA), classifiers for the target domain a...

Learning from a Complementary-label Source Domain: Theory and Algorithms

In unsupervised domain adaptation (UDA), a classifier for the target dom...