CSNet: Cross-Stage Subtraction Network for Real-Time Semantic Segmentation in Autonomous Driving

Learning multi-scale feature representations is essential for dense prediction tasks in autonomous driving. Most existing works are based on U-shaped architectures, where high-resolution representations are progressively recovered by connecting different levels of the decoder with low-resolution rep...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on intelligent transportation systems 2024-12, p.1-16
Hauptverfasser:	Elhassan, Mohammed A. M., Zhou, Changjun, Zhu, Donglin, Adam, Abuzar B. M., Benabid, Amina, Khan, Ali, Mehmood, Atif, Zhang, Jun, Jin, Hu, Jeon, Sang-Woon
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Autonomous vehicles Computer architecture Computer science context reasoning Convolution cross-stage subtraction Electronic mail Feature extraction graph convolution network (GCN) high-resolution Real-time semantic segmentation Real-time systems Semantic segmentation Semantics
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!