Boosting Deep Unsupervised Edge Detection via Segment Anything Model

Segment anything model (SAM), a vision foundation network trained on a massive segmentation corpus, exhibits a superior boundary localization capability for nature images. This work aims to leverage such strengths to develop a deep unsupervised edge detection (UED) framework for alleviating the high...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on industrial informatics 2024-06, Vol.20 (6), p.8961-8971
Hauptverfasser:	Yang, Wenya, Chen, Xiao-Diao, Wu, Wen, Qin, Hongshuai, Yan, Kangming, Mao, Xiaoyang, Song, Haichuan
Format:	Artikel
Sprache:	eng
Schlagworte:	Detection algorithms Edge detection Feature extraction Image edge detection Labels Noise measurement segment anything model (SAM) Segments self-learning Task analysis Training Transformers unsupervised learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!