Multi-view and multi-augmentation for self-supervised visual representation learning

In the real world, the appearance of identical objects depends on factors as varied as resolution, angle, illumination conditions, and viewing perspectives. This suggests that the data augmentation pipeline could benefit downstream tasks by exploring the overall data appearance in a self-supervised...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Applied intelligence (Dordrecht, Netherlands) Netherlands), 2024, Vol.54 (1), p.629-656
Hauptverfasser:	Tran, Van Nhiem, Huang, Chi-En, Liu, Shen-Hsuan, Aslam, Muhammad Saqlain, Yang, Kai-Lin, Li, Yung-Hui, Wang, Jia-Ching
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial Intelligence Color Computer Science Data augmentation Distortion Efficiency Invariants Machine learning Machines Manufacturing Mechanical Engineering Methods Object recognition Processes Representations Self-supervised learning Semantics
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!