ContraCluster: Learning to Classify without Labels by Contrastive Self-Supervision and Prototype-Based Semi-Supervision

The recent advances in representation learning inspire us to take on the challenging problem of unsupervised image classification tasks in a principled way. We propose ContraCluster, an unsupervised image classification method that combines clustering with the power of contrastive self-supervised le...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-04
Hauptverfasser:	Seongho Joe, Kim, Byoungjip, Kang, Hoyoung, Park, Kyoungwon, Bogun Kim, Park, Jaeseon, Lee, Joonseok, Gwon, Youngjune
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Clustering Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning Image classification Labels Prototypes Self-supervised learning
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!