Authors:
Kim Bjerge
1
;
Paul Bodesheim
2
and
Henrik Karstoft
1
Affiliations:
1
Department of Electrical and Computer Engineering, Aarhus University, Finlandsgade 22, 8200 Aarhus N, Denmark
;
2
Computer Vision Group, Friedrich Schiller University, Ernst-Abbe-Platz 2, 07743 Jena, Germany
Keyword(s):
Deep Clustering, Episodic Training, Few-Shot Learning, Multivariate Loss, Semi-Supervised Learning.
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 Le
arning 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.
(More)