Weakly-Supervised Camouflaged Object Detection with Scribble Annotations

Existing camouflaged object detection (COD) methods rely heavily on large-scale datasets with pixel-wise annotations. However, due to the ambiguous boundary, annotating camouflage objects pixel-wisely is very time-consuming and labor-intensive, taking ~60mins to label one image. In this paper, we pr...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-11
Hauptverfasser:	He, Ruozhen, Dong, Qihua, Lin, Jiaying, Lau, Rynson W H
Format:	Artikel
Sprache:	eng
Schlagworte:	Annotations Consistency Datasets Feature extraction Object recognition Pixels Semantics
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!