Information maximization clustering via multi-view self-labelling

Ntelemis F, Jin Y, Thomas SA (2022)
Knowledge-Based Systems 250: 109042.

Zeitschriftenaufsatz | Veröffentlicht | Englisch
 
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Ntelemis, Foivos; Jin, YaochuUniBi; Thomas, Spencer A.
Abstract / Bemerkung
Image clustering is a particularly challenging computer vision task, which aims to generate annotations without human supervision. Recent advances focus on the use of self-supervised learning strategies in image clustering, by first learning valuable semantics and then clustering the image representations. These multiple-phase algorithms, however, involve several hyper-parameters and transformation functions, and are computationally intensive. By extending the grouping based self-supervised approach, this work proposes a novel single-phase clustering method that simultaneously learns meaningful representations and assigns the corresponding annotations. This is achieved by integrating a discrete representation into the self-supervised paradigm through a classifier net. Specifically, the proposed clustering objective employs mutual information to maximise the dependency of the integrated discrete representation on a discrete probability distribution. The discrete probability distribution is derived by means of a self-supervised process that compares the learnt latent representation with a set of trainable prototypes. To enhance the learning performance of the classifier, we jointly apply the mutual information across multi-crop views. Our empirical results show that the proposed framework outperforms state-of-the-art techniques with an average clustering accuracy of 89.1%, 49.0%, 83.1%, and 27.9%, respectively, on the baseline datasets of CIFAR-10, CIFAR-100/20, STL10 and Tiny-ImageNet/200. Finally, the proposed method also demonstrates attractive robustness to parameter settings, and to a large number of classes, making it ready to be applicable to other datasets. (c) 2022 Elsevier B.V. All rights reserved.
Stichworte
Deep neural models; Mutual information maximization; Unsupervised; learning; Self-supervised learning; Image clustering
Erscheinungsjahr
2022
Zeitschriftentitel
Knowledge-Based Systems
Band
250
Art.-Nr.
109042
ISSN
0950-7051
eISSN
1872-7409
Page URI
https://pub.uni-bielefeld.de/record/2964349

Zitieren

Ntelemis F, Jin Y, Thomas SA. Information maximization clustering via multi-view self-labelling. Knowledge-Based Systems. 2022;250: 109042.
Ntelemis, F., Jin, Y., & Thomas, S. A. (2022). Information maximization clustering via multi-view self-labelling. Knowledge-Based Systems, 250, 109042. https://doi.org/10.1016/j.knosys.2022.109042
Ntelemis, F., Jin, Y., and Thomas, S. A. (2022). Information maximization clustering via multi-view self-labelling. Knowledge-Based Systems 250:109042.
Ntelemis, F., Jin, Y., & Thomas, S.A., 2022. Information maximization clustering via multi-view self-labelling. Knowledge-Based Systems, 250: 109042.
F. Ntelemis, Y. Jin, and S.A. Thomas, “Information maximization clustering via multi-view self-labelling”, Knowledge-Based Systems, vol. 250, 2022, : 109042.
Ntelemis, F., Jin, Y., Thomas, S.A.: Information maximization clustering via multi-view self-labelling. Knowledge-Based Systems. 250, : 109042 (2022).
Ntelemis, Foivos, Jin, Yaochu, and Thomas, Spencer A. “Information maximization clustering via multi-view self-labelling”. Knowledge-Based Systems 250 (2022): 109042.

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Web of Science

Dieser Datensatz im Web of Science®

Suchen in

Google Scholar