DeepAI AI Chat
Log In Sign Up

Open Set Domain Adaptation By Novel Class Discovery

03/07/2022
by   Jingyu Zhuang, et al.
IEEE
SUN YAT-SEN UNIVERSITY
0

In Open Set Domain Adaptation (OSDA), large amounts of target samples are drawn from the implicit categories that never appear in the source domain. Due to the lack of their specific belonging, existing methods indiscriminately regard them as a single class unknown. We challenge this broadly-adopted practice that may arouse unexpected detrimental effects because the decision boundaries between the implicit categories have been fully ignored. Instead, we propose Self-supervised Class-Discovering Adapter (SCDA) that attempts to achieve OSDA by gradually discovering those implicit classes, then incorporating them to restructure the classifier and update the domain-adaptive features iteratively. SCDA performs two alternate steps to achieve implicit class discovery and self-supervised OSDA, respectively. By jointly optimizing for two tasks, SCDA achieves the state-of-the-art in OSDA and shows a competitive performance to unearth the implicit target classes.

READ FULL TEXT

page 1

page 2

page 3

page 4

07/30/2019

Open Set Domain Adaptation for Image and Action Recognition

Since annotating and curating large datasets is very expensive, there is...
07/24/2020

On the Effectiveness of Image Rotation for Open Set Domain Adaptation

Open Set Domain Adaptation (OSDA) bridges the domain gap between a label...
02/19/2020

Universal Domain Adaptation through Self Supervision

Unsupervised domain adaptation methods traditionally assume that all sou...
11/04/2020

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...
07/10/2022

Towards Adaptive Unknown Authentication for Universal Domain Adaptation by Classifier Paradox

Universal domain adaptation (UniDA) is a general unsupervised domain ada...
08/06/2019

Attract or Distract: Exploit the Margin of Open Set

Open set domain adaptation aims to diminish the domain shift across doma...
05/06/2021

Towards Novel Target Discovery Through Open-Set Domain Adaptation

Open-set domain adaptation (OSDA) considers that the target domain conta...