Downsampling Algorithm with Fusion of Different Receptive Field Sizes in Deep Detection Methods

The advantage of deep detection models primarily benefits from the feature representation ability of the backbone network, where down-sampling plays a key role in semantic integration. However, existing down-sampling approaches often ignore the global structural information of features, due to the u...

Szczegółowa specyfikacja

Opis bibliograficzny

1. autor:	GU Zhenghua, LIU Gaqiong, SHAO Changbin, YU Hualong
Format:	Artigo
Język:	Chinês
Wydane:	Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press 2024-10-01
Seria:	Jisuanji kexue yu tansuo
Hasła przedmiotowe:	deep learning; deep object detection; multi-scale object detection; down-sampling strategy
Dostęp online:	http://fcst.ceaj.org/fileup/1673-9418/PDF/2308064.pdf
Etykiety:	Dodaj etykietę Nie ma etykietki, Dołącz pierwszą etykiete!