Diff-SySC: An Approach Using Diffusion Models for Semi-Supervised Image Classification

Paul-Dumitru Orășan, Alexandra-Ioana Albu, Gabriela Czibula

2025

Abstract

Diffusion models have revolutionized the field of generative machine learning due to their effectiveness in capturing complex, multimodal data distributions. Semi-supervised learning represents a technique that allows the extraction of information from a large corpus of unlabeled data, assuming that a small subset of labeled data is provided. While many generative methods have been previously used in semi-supervised learning tasks, only few approaches have integrated diffusion models in such a context. In this work, we are adapting state-of-the-art generative diffusion models to the problem of semi-supervised image classification. We propose Diff-SySC, a new semi-supervised, pseudo-labeling pipeline which uses a diffusion model to learn the conditional probability distribution characterizing the label generation process. Experimental evaluations highlight the robustness of Diff-SySC when evaluated on image classification benchmarks and show that it outperforms related work approaches on CIFAR-10 and STL-10, while achieving competitive performance on CIFAR-100. Overall, our proposed method outperforms the related work in 90.74% of the cases.

Paper Citation

in Harvard Style

Orășan P., Albu A. and Czibula G. (2025). Diff-SySC: An Approach Using Diffusion Models for Semi-Supervised Image Classification. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 132-139. DOI: 10.5220/0013097100003890

in Bibtex Style

@conference{icaart25,
author={Paul-Dumitru Orășan and Alexandra-Ioana Albu and Gabriela Czibula},
title={Diff-SySC: An Approach Using Diffusion Models for Semi-Supervised Image Classification},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2025},
pages={132-139},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013097100003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Diff-SySC: An Approach Using Diffusion Models for Semi-Supervised Image Classification
SN - 978-989-758-737-5
AU - Orășan P.
AU - Albu A.
AU - Czibula G.
PY - 2025
SP - 132
EP - 139
DO - 10.5220/0013097100003890
PB - SciTePress