Ring-Masked Attention Network for Rotation-Invariant Template-Matching

To solve the rotational changes in matching localization of an underwater terrain image, this letter proposes the ring-masked attention network (RMANet), a model-driven deep network for rotational template-matching tasks. Since traditional convolutional neural networks cannot effectively encode rota...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE signal processing letters 2023-01, Vol.30, p.1-5
Hauptverfasser:	Zhang, Feng, Bian, HongYu, Lv, Zheng, Zhai, YuFeng
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Computational modeling Convolutional neural networks Feature extraction Invariants Location awareness ring-projection transform Rotation rotational equivariance rotational invariance Template matching Training Transforms Underwater vehicles
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!