Ghostformer: A GhostNet-Based Two-Stage Transformer for Small Object Detection

In this paper, we propose a novel two-stage transformer with GhostNet, which improves the performance of the small object detection task. Specifically, based on the original Deformable Transformers for End-to-End Object Detection (deformable DETR), we chose GhostNet as the backbone to extract featur...

Full beskrivning

Bibliografiska uppgifter

Huvudupphov:	Sijia Li, Furkat Sultonov, Jamshid Tursunboev, Jun-Hyun Park, Sangseok Yun, Jae-Mo Kang
Materialtyp:	Artigo
Språk:	Inglês
Utgiven:	MDPI AG 2022-09-01
Serie:	Sensors
Ämnen:	small object detection GhostNet <i>regional proposals</i> two-stage transformer
Länkar:	https://www.mdpi.com/1424-8220/22/18/6939
Taggar:	Lägg till en tagg Inga taggar, Lägg till första taggen!