Improving Pseudo-Labelling and Enhancing Robustness for Semi-Supervised Domain Generalization

Authors

Adnan Khan, Mohamed bin Zayed University of Artificial IntelligenceFollow
Mai A. Shaaban, Mohamed bin Zayed University of Artificial IntelligenceFollow
Muhammad Haris Khan, Mohamed bin Zayed University of Artificial IntelligenceFollow

Document Type

Conference Proceeding

Publication Title

Proceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

Abstract

Beyond attaining domain generalization (DG), visual recognition models should also be data-efficient during learning by leveraging limited labels. We study the problem of Semi-Supervised Domain Generalization (SSDG) which is crucial for real-world applications like automated healthcare. SSDG requires learning a cross-domain generalizable model when the given training data is only partially labelled. Empirical investigations reveal that the DG methods tend to underperform in SSDG settings, likely because they are unable to exploit the unlabelled data. Semi-supervised learning (SSL) shows improved but still inferior results compared to fully-supervised learning. A key challenge, faced by the best performing SSL-based SSDG methods, is selecting accurate pseudo-labels under multiple domain shifts and reducing overfitting to source domains under limited labels. In this work, we propose new SSDG approach, which utilizes a novel uncertainty-guided pseudo-labelling with model averaging (UPLM). Our uncertainty-guided pseudo-labelling (UPL) uses model uncertainty to improve pseudo-labelling selection, addressing poor model calibration under multi-source unlabelled data. The UPL technique, enhanced by our novel model averaging (MA) strategy, mitigates overfitting to source domains with limited labels. Extensive experiments on key representative DG datasets suggest that our method demonstrates effectiveness against existing methods. Our code and chosen labelled data seeds are available on GitHub: https://github.com/Adnan-Khan7/UPLM.

First Page

293

Last Page

300

DOI

10.5220/0012269400003660

Publication Date

1-1-2024

Keywords

Domain Generalization, Semi-Supervised Learning, Transfer Learning, Visual Recognition

Recommended Citation

A. Khan et al., "Improving Pseudo-Labelling and Enhancing Robustness for Semi-Supervised Domain Generalization," Proceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, vol. 2, pp. 293 - 300, Jan 2024.

The definitive version is available at https://doi.org/10.5220/0012269400003660