Leveraging Permuted Image Restoration for Improved Interpretation of Remote Sensing Images

In this study, we introduce a novel self-supervised learning adapter based on permutated image restoration (PIR) for effectively transferring pretrained weights from natural images to remote sensing object detection tasks. The adapter's unique methodology encompasses a three-phase process: segm...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on geoscience and remote sensing 2024, Vol.62, p.1-15
Hauptverfasser:	Bai, Awen, Chen, Jie, Yang, Wei, Men, Zhirong, Zhang, Shengming, Zeng, Hongcheng, Xu, Weichen, Cao, Jian
Format:	Artikel
Sprache:	eng
Schlagworte:	Adapters Collections Datasets Detection Feature extraction Image restoration Image segmentation Object detection Object recognition Oriented object detection permutated image restoration (PIR) permutation matrix estimation Permutations pretrained weights Radar data Remote sensing Restoration SAR (radar) Self-supervised learning Ships Synthetic aperture radar Task analysis
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!