Open Set Domain Adaptation by Backpropagation

by   Kuniaki Saito, et al.

Numerous algorithms have been proposed for transferring knowledge from a label-rich domain (source) to a label-scarce domain (target). Almost all of them are proposed for a closed-set scenario, where the source and the target domain completely share the class of their samples. We call the shared class the known class. However, in practice, when samples in target domain are not labeled, we cannot know whether the domains share the class. A target domain can contain samples of classes that are not shared by the source domain. We call such classes the unknown class and algorithms that work well in the open set situation are very practical. However, most existing distribution matching methods for domain adaptation do not work well in this setting because unknown target samples should not be aligned with the source. In this paper, we propose a method for an open set domain adaptation scenario which utilizes adversarial training. A classifier is trained to make a boundary between the source and the target samples whereas a generator is trained to make target samples far from the boundary. Thus, we assign two options to the feature generator: aligning them with source known samples or rejecting them as unknown target samples. This approach allows extracting features that separate unknown target samples from known target samples. Our method was extensively evaluated in domain adaptation setting and outperformed other methods with a large margin in most settings.


page 13

page 19


Divergence Optimization for Noisy Universal Domain Adaptation

Universal domain adaptation (UniDA) has been proposed to transfer knowle...

OVANet: One-vs-All Network for Universal Domain Adaptation

Universal Domain Adaptation (UNDA) aims to handle both domain-shift and ...

Attract or Distract: Exploit the Margin of Open Set

Open set domain adaptation aims to diminish the domain shift across doma...

Towards Adaptive Unknown Authentication for Universal Domain Adaptation by Classifier Paradox

Universal domain adaptation (UniDA) is a general unsupervised domain ada...

A Primer on Domain Adaptation

Standard supervised machine learning assumes that the distribution of th...

Conditional Extreme Value Theory for Open Set Video Domain Adaptation

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

Against Adversarial Learning: Naturally Distinguish Known and Unknown in Open Set Domain Adaptation

Open set domain adaptation refers to the scenario that the target domain...

Please sign up or login with your details

Forgot password? Click here to reset