Improving unsupervised image clustering with spatial consistency

Unsupervised image clustering (UIC) is regularly employed to group images without manual annotation. One significant problem that occurs in the UIC context is that the visual-feature similarity across different semantic classes tends to introduce instance-dependent errors to clustering. The most suc...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Knowledge-based systems 2022-06, Vol.246, p.108673, Article 108673
Hauptverfasser:	Zhao, Rui, Ruan, Jianfei, Dong, Bo, Meng, Li, Zhang, Weizhan
Format:	Artikel
Sprache:	eng
Schlagworte:	Alignment Annotations Clustering Consistency Reclustering Reliability analysis Representation consistency Representations Semantics Unsupervised image clustering
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!