Adjustment and Alignment for Unbiased Open Set Domain Adaptation

Wuyang Li, Jie Liu, Bo Han, Yixuan Yuan*

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

6 Citations (Scopus)

Abstract

Open Set Domain Adaptation (OSDA) transfers the model from a label-rich domain to a label-free one containing novel-class samples. Existing OSDA works overlook abundant novel-class semantics hidden in the source domain, leading to a biased model learning and transfer. Although the causality has been studied to remove the semantic-level bias, the non-available novel-class samples result in the failure of existing causal solutions in OSDA. To break through this barrier, we propose a novel causality-driven solution with the unexplored front-door adjustment theory, and then implement it with a theoretically grounded framework, coined Adjustment and Alignment (ANNA), to achieve an unbiased OSDA. In a nutshell, ANNA consists of Front-Door Adjustment (FDA) to correct the biased learning in the source domain and Decoupled Causal Alignment (DCA) to transfer the model unbiasedly. On the one hand, FDA delves into fine-grained visual blocks to discover novel-class regions hidden in the base-class image. Then, it corrects the biased model optimization by implementing causal debiasing. On the other hand, DCA disentangles the base-class and novel-class regions with orthogonal masks, and then adapts the decoupled distribution for an unbiased model transfer. Extensive experiments show that ANNA achieves state-of-the-art results. The code is available at https://github.com/CityU-AIM-Group/Anna.

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
PublisherIEEE
Pages24110-24119
Number of pages10
ISBN (Electronic)9798350301298
ISBN (Print)9798350301304
DOIs
Publication statusPublished - 17 Jun 2023
Event36th IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 - Vancouver, Canada
Duration: 17 Jun 202322 Jun 2023
https://cvpr2023.thecvf.com/
https://openaccess.thecvf.com/CVPR2023
https://ieeexplore.ieee.org/xpl/conhome/10203037/proceeding

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2023-June
ISSN (Print)1063-6919
ISSN (Electronic)2575-7075

Conference

Conference36th IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
Country/TerritoryCanada
CityVancouver
Period17/06/2322/06/23
Internet address

Scopus Subject Areas

  • Software
  • Computer Vision and Pattern Recognition

User-Defined Keywords

  • continual
  • low-shot
  • meta
  • or long-tail learning
  • Transfer

Fingerprint

Dive into the research topics of 'Adjustment and Alignment for Unbiased Open Set Domain Adaptation'. Together they form a unique fingerprint.

Cite this