On the instability of unsupervised domain adaptation with ADDA

Kazuki Omi; Toru Tamaki

doi:10.1117/12.2625953

30 April 2022 On the instability of unsupervised domain adaptation with ADDA

Kazuki Omi, Toru Tamaki

Proceedings Volume 12177, International Workshop on Advanced Imaging Technology (IWAIT) 2022; 121771X (2022) https://doi.org/10.1117/12.2625953
Event: International Workshop on Advanced Imaging Technology 2022 (IWAIT 2022), 2022, Hong Kong, China

Abstract

In this paper we report the instability of Adversarial Discriminative Domain Adaptation (ADDA), an unsupervised domain adaptation. The accuracy of ADDA is not stable, and we show that the instability comes from the initialization of CNN for the target domain, not from the pre-training with the source domain.

Citation Download Citation

Kazuki Omi and Toru Tamaki "On the instability of unsupervised domain adaptation with ADDA", Proc. SPIE 12177, International Workshop on Advanced Imaging Technology (IWAIT) 2022, 121771X (30 April 2022); https://doi.org/10.1117/12.2625953

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available