Causality-inspired comparative learning supervised model for domain generalization

Xiaosong Zhu; Bin Yang; Jingfeng Guo; Genghuang Yang

doi:10.1117/12.3021261

25 March 2024 Causality-inspired comparative learning supervised model for domain generalization

Xiaosong Zhu, Bin Yang, Jingfeng Guo, Genghuang Yang

Proceedings Volume 13089, Fifteenth International Conference on Graphics and Image Processing (ICGIP 2023); 1308903 (2024) https://doi.org/10.1117/12.3021261
Event: Fifteenth International Conference on Graphics and Image Processing (ICGIP 2023), 2023, Suzhou, China

Abstract

Machine learning is good at learning general knowledge and predictive knowledge from known and limited environments, and perform well in similar environments. However, their performance in unknown environments is not satisfactory. Machine learning focus on correlation learning, but correlation is not causality. The non-causal part of the correlation forms spurious correlation that affect the model's generalization ability. Therefore, it is necessary to examine machine learning from a causal perspective. By constructing structural causal models, it is found that the targets of different domains are instrumental variables of each other and can be mutually represented. They have same essential features and different domain features, which lead to causal correlation and spurious correlation with labels respectively. In this paper, a causal-inspired contrastive learning supervised model is designed to strengthen essential features and weaken domain features. With the target of improving the ability of model to capture causal correlations and reducing the interference of spurious correlations, we join transfer and autoencoder with image classification model as a cross-domain contrastive learning model. Experiments show that the proposed framework has a simple and easy-to-implement structure, it performs well on public datasets. By adopting visualization technology, the effects of this method are intuitively demonstrated.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Xiaosong Zhu, Bin Yang, Jingfeng Guo, and Genghuang Yang "Causality-inspired comparative learning supervised model for domain generalization", Proc. SPIE 13089, Fifteenth International Conference on Graphics and Image Processing (ICGIP 2023), 1308903 (25 March 2024); https://doi.org/10.1117/12.3021261

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
14 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Machine learning

Education and training

Feature extraction

Visualization

Data modeling

Picture Archiving and Communication System

Adversarial training

Show All Keywords

Keywords/Phrases

Search In:

Publication Years