SnipeDet: Attention-guided pyramidal prediction kernels for generic object detection

•APPK module is proposed to tackle misalignments of different scales of objects.•IoU-adaptive loss function helps networks to deal with the hard negative samples.•SORR module is devised to improve the detection efficiency.•Interleaved subsampling method can enhance feature representations. Using sin...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Pattern recognition letters 2021-12, Vol.152, p.302-310
Hauptverfasser:	Chen, Suting, Cheng, Zehua, Zhang, Liangchen, Zheng, Yujie
Format:	Artikel
Sprache:	eng
Schlagworte:	Attention mechanism Detectors Feature enhancement Feature maps Hard negative mining Kernels Misalignment Modules Object detection Object recognition Prediction module Predictions Salience Sensors
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!