Progressively Select and Reject Pseudo-labelled Samples for Open-Set Domain Adaptation

by   Qian Wang, et al.

Domain adaptation solves image classification problems in the target domain by taking advantage of the labelled source data and unlabelled target data. Usually, the source and target domains share the same set of classes. As a special case, Open-Set Domain Adaptation (OSDA) assumes there exist additional classes in the target domain but not present in the source domain. To solve such a domain adaptation problem, our proposed method learns discriminative common subspaces for the source and target domains using a novel Open-Set Locality Preserving Projection (OSLPP) algorithm. The source and target domain data are aligned in the learned common spaces class-wisely. To handle the open-set classification problem, our method progressively selects target samples to be pseudo-labelled as known classes and rejects the outliers if they are detected as from unknown classes. The common subspace learning algorithm OSLPP simultaneously aligns the labelled source data and pseudo-labelled target data from known classes and pushes the rejected target data away from the known classes. The common subspace learning and the pseudo-labelled sample selection/rejection facilitate each other in an iterative learning framework and achieves state-of-the-art performance on benchmark datasets Office-31 and Office-Home with the average HOS of 87.4


page 1

page 2

page 3

page 4


Open Set Domain Adaptation by Extreme Value Theory

Common domain adaptation techniques assume that the source domain and th...

Unifying Unsupervised Domain Adaptation and Zero-Shot Visual Recognition

Unsupervised domain adaptation aims to transfer knowledge from a source ...

Conditional Extreme Value Theory for Open Set Video Domain Adaptation

With the advent of media streaming, video action recognition has become ...

Source-Free Progressive Graph Learning for Open-Set Domain Adaptation

Open-set domain adaptation (OSDA) has gained considerable attention in m...

A Sample Selection Approach for Universal Domain Adaptation

We study the problem of unsupervised domain adaption in the universal sc...

Target Domain Data induces Negative Transfer in Mixed Domain Training with Disjoint Classes

In practical scenarios, it is often the case that the available training...

Unsupervised Cross-Domain Recognition by Identifying Compact Joint Subspaces

This paper introduces a new method to solve the cross-domain recognition...

Please sign up or login with your details

Forgot password? Click here to reset