Attention-based supervised contrastive learning on fine-grained image classification

To solve the problem of fine-grained image classification performance caused by intra-class diversity and inter-class similarity in fine-grained images, we propose an Attention-based Supervised Contrastive (ASC) algorithm for fine-grained image classification. The method involves three stages: first...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Pattern analysis and applications : PAA 2024-09, Vol.27 (3), Article 96
Hauptverfasser:	Li, Qian, Wu, Weining
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Computer Science Entropy (Information theory) Image classification Pattern Recognition Theoretical Advances
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!