Uni-EPM: A Unified Extensible Perception Model Without Labeling Everything

Multi-task perception system to simultaneously perceive various kinds of objects is essential for autonomous driving. Existing perception frameworks always rely on multi-labeled datasets, which encompass labels for all pertinent objects, thereby constraining their adaptability to leverage specialize...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on intelligent transportation systems 2025-01, Vol.26 (1), p.1-13
Hauptverfasser:	Gao, Yilin, Mu, Shiyi, Xu, Shugong
Format:	Artikel
Sprache:	eng
Schlagworte:	Autonomous vehicles Computational modeling Decoding Feature extraction Image segmentation Incremental learning Multi-task Multitasking panoptic driving perception Semantics Training unified framework Vocabulary
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!