SCDet: decoupling discriminative representation for dark object detection via supervised contrastive learning

Despite the significant progress made in object detection algorithms, their potential to operate effectively under the low-light environment remains to be fully explored. Recent methods realize dark object detection on the entire representation of dark images; however, they do not further consider t...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	The Visual computer 2024-05, Vol.40 (5), p.3357-3369
Hauptverfasser:	Lin, Tongxu, Huang, Guoheng, Yuan, Xiaochen, Zhong, Guo, Huang, Xiaocong, Pun, Chi-Man
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Artificial Intelligence Computer Graphics Computer Science Datasets Decoding Decoupling Entanglement Image Processing and Computer Vision Light Object recognition Optimization Original Article Representations Sensors
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!