Deep Image Clustering with Model-Agnostic Meta-Learning

Kim Bjerge, Paul Bodesheim, Henrik Karstoft

2025

Abstract

Deep clustering has proven successful in analyzing complex, high-dimensional real-world data. Typically, features are extracted from a deep neural network and then clustered. However, training the network to extract features that can be clustered efficiently in a semantically meaningful way is particularly challenging when data is sparse. In this paper, we present a semi-supervised method to fine-tune a deep learning network using Model-Agnostic Meta-Learning, commonly employed in Few-Shot Learning. We apply episodic training with a novel multivariate scatter loss, designed to enhance inter-class feature separation while minimizing intra-class variance, thereby improving overall clustering performance. Our approach works with state-of-the-art deep learning models, spanning convolutional neural networks and vision transformers, as well as different clustering algorithms like K-means and Spectral clustering. The effectiveness of our method is tested on several commonly used Few-Shot Learning datasets, where episodic fine-tuning with our multivariate scatter loss and a ConvNeXt backbone outperforms other models, achieving adjusted rand index scores of 89.7% on the EU moths dataset and 86.9% on the Caltech birds dataset, respectively. Hence, our proposed method can be applied across various practical domains, such as clustering images of animal species in biology.

Paper Citation

in Harvard Style

Bjerge K., Bodesheim P. and Karstoft H. (2025). Deep Image Clustering with Model-Agnostic Meta-Learning. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 286-297. DOI: 10.5220/0013114600003912

in Bibtex Style

@conference{visapp25,
author={Kim Bjerge and Paul Bodesheim and Henrik Karstoft},
title={Deep Image Clustering with Model-Agnostic Meta-Learning},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2025},
pages={286-297},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013114600003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Deep Image Clustering with Model-Agnostic Meta-Learning
SN - 978-989-758-728-3
AU - Bjerge K.
AU - Bodesheim P.
AU - Karstoft H.
PY - 2025
SP - 286
EP - 297
DO - 10.5220/0013114600003912
PB - SciTePress