Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation

07/29/2020
by   Yiyang Zhang, et al.
6

In unsupervised domain adaptation (UDA), classifiers for the target domain are trained with massive true-label data from the source domain and unlabeled data from the target domain. However, it may be difficult to collect fully-true-label data in a source domain given a limited budget. To mitigate this problem, we consider a novel problem setting where the classifier for the target domain has to be trained with complementary-label data from the source domain and unlabeled data from the target domain named budget-friendly UDA (BFUDA). The key benefit is that it is much less costly to collect complementary-label source data (required by BFUDA) than collecting the true-label source data (required by ordinary UDA). To this end, the complementary label adversarial network (CLARINET) is proposed to solve the BFUDA problem. CLARINET maintains two deep networks simultaneously, where one focuses on classifying complementary-label source data and the other takes care of the source-to-target distributional adaptation. Experiments show that CLARINET significantly outperforms a series of competent baselines.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 6

page 7

research
08/04/2020

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

In unsupervised domain adaptation (UDA), a classifier for the target dom...
research
06/11/2021

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

In few-shot domain adaptation (FDA), classifiers for the target domain a...
research
01/01/2020

Low-Budget Unsupervised Label Query through Domain Alignment Enforcement

Deep learning revolution happened thanks to the availability of a massiv...
research
08/24/2020

Improved Mutual Mean-Teaching for Unsupervised Domain Adaptive Re-ID

In this technical report, we present our submission to the VisDA Challen...
research
04/22/2023

Weight-based Mask for Domain Adaptation

In computer vision, unsupervised domain adaptation (UDA) is an approach ...
research
03/19/2020

Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering

Unsupervised domain adaptation (UDA) is to make predictions for unlabele...

Please sign up or login with your details

Forgot password? Click here to reset