A Review of DEtection TRansformer: From Basic Architecture to Advanced Developments and Visual Perception Applications

DEtection TRansformer (DETR) introduced an end-to-end object detection paradigm using Transformers, eliminating hand-crafted components like anchor boxes and Non-Maximum Suppression (NMS) via set prediction and bipartite matching. Despite its potential, the original DETR suffered from slow convergen...

Descripció completa

Dades bibliogràfiques

Autors principals:	Liang Yu, Lin Tang, Lisha Mu
Format:	Artigo
Idioma:	Inglês
Publicat:	MDPI AG 2025-06-01
Col·lecció:	Sensors
Matèries:	object detection DETR transformer attention end to end deep learning
Accés en línia:	https://www.mdpi.com/1424-8220/25/13/3952
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!