Dual semantic-guided model for weakly-supervised zero-shot semantic segmentation

The major obstacle in semantic segmentation is that it requires a large number of pixel-level labeled data to train an effective model. In order to reduce the cost of annotation, weakly-supervised methods use weaker labels to overcome the need for per-pixel labels, while zero-shot methods transfer t...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Multimedia tools and applications 2022-02, Vol.81 (4), p.5443-5458
Hauptverfasser:	Shen, Fengli, Lu, Zhe-Ming, Lu, Ziqian, Wang, Zonghui
Format:	Artikel
Sprache:	eng
Schlagworte:	Classification Computer Communication Networks Computer Science Data Structures and Information Theory Image annotation Image segmentation Knowledge management Labels Localization Multimedia Information Systems Pixels Semantic segmentation Semantics Special Purpose and Application-Based Systems
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!