Domain Gap Estimation for Source Free Unsupervised Domain Adaptation with Many Classifiers

by   Ziyang Zong, et al.

In theory, the success of unsupervised domain adaptation (UDA) largely relies on domain gap estimation. However, for source free UDA, the source domain data can not be accessed during adaptation, which poses great challenge of measuring the domain gap. In this paper, we propose to use many classifiers to learn the source domain decision boundaries, which provides a tighter upper bound of the domain gap, even if both of the domain data can not be simultaneously accessed. The source model is trained to push away each pair of classifiers whilst ensuring the correctness of the decision boundaries. In this sense, our many classifiers model separates the source different categories as far as possible which induces the maximum disagreement of many classifiers in the target domain, thus the transferable source domain knowledge is maximized. For adaptation, the source model is adapted to maximize the agreement among pairs of the classifiers. Thus the target features are pushed away from the decision boundaries. Experiments on several datasets of UDA show that our approach achieves state of the art performance among source free UDA approaches and can even compete to source available UDA methods.


page 1

page 2

page 3

page 4


Unsupervised Domain Adaptation without Source Data by Casting a BAIT

Unsupervised domain adaptation (UDA) aims to transfer the knowledge lear...

Domain Consistency Regularization for Unsupervised Multi-source Domain Adaptive Classification

Deep learning-based multi-source unsupervised domain adaptation (MUDA) h...

Adversarial Dual Distinct Classifiers for Unsupervised Domain Adaptation

Unsupervised Domain adaptation (UDA) attempts to recognize the unlabeled...

Unsupervised Domain Adaptation Through Transferring both the Source-Knowledge and Target-Relatedness Simultaneously

Unsupervised domain adaptation (UDA) is an emerging research topic in th...

Distributionally Robust Learning for Unsupervised Domain Adaptation

We propose a distributionally robust learning (DRL) method for unsupervi...

Multi-step Online Unsupervised Domain Adaptation

In this paper, we address the Online Unsupervised Domain Adaptation (OUD...

Please sign up or login with your details

Forgot password? Click here to reset