A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation

by   Jian Liang, et al.

This work addresses the unsupervised domain adaptation problem, especially for the partial scenario where the class labels in the target domain are only a subset of those in the source domain. Such a partial transfer setting sounds realistic but challenging while existing methods always suffer from two key problems, i.e., negative transfer and uncertainty propagation. In this paper, we build on domain adversarial learning and propose a novel domain adaptation method BA^3US with two new techniques termed Balanced Adversarial Alignment (BAA) and Adaptive Uncertainty Suppression (AUS), respectively. On one hand, negative transfer results in that target samples are misclassified to the classes only present in the source domain. To address this issue, BAA aims to pursue the balance between label distributions across domains in a quite simple manner. Specifically, it randomly leverages a few source samples to augment the smaller target domain during domain alignment so that classes in different domains are symmetric. On the other hand, a source sample is denoted as uncertain if there is an incorrect class that has a relatively high prediction score. Such uncertainty is easily propagated to the unlabeled target data around it during alignment, which severely deteriorates the adaptation performance. Thus, AUS emphasizes uncertain samples and exploits an adaptive weighted complement entropy objective to expect that incorrect classes have the uniform and low prediction scores. Experimental results on multiple benchmarks demonstrate that BA^3US surpasses state-of-the-arts for partial domain adaptation tasks.


page 1

page 2

page 3

page 4


TWINs: Two Weighted Inconsistency-reduced Networks for Partial Domain Adaptation

The task of unsupervised domain adaptation is proposed to transfer the k...

Importance Weighted Adversarial Nets for Partial Domain Adaptation

This paper proposes an importance weighted adversarial nets-based method...

Associative Partial Domain Adaptation

Partial Adaptation (PDA) addresses a practical scenario in which the tar...

Partial Domain Adaptation without Domain Alignment

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a w...

Domain Adversarial Reinforcement Learning for Partial Domain Adaptation

Partial domain adaptation aims to transfer knowledge from a label-rich s...

mDALU: Multi-Source Domain Adaptation and Label Unification with Partial Datasets

Object recognition advances very rapidly these days. One challenge is to...

Coupling Adversarial Learning with Selective Voting Strategy for Distribution Alignment in Partial Domain Adaptation

In contrast to a standard closed-set domain adaptation task, partial dom...