Learning What Not to Segment: A New Perspective on Few-Shot Segmentation

Recently few-shot segmentation (FSS) has been extensively developed. Most previous works strive to achieve generalization through the meta-learning framework derived from classification tasks; however, the trained models are biased towards the seen classes instead of being ideally class-agnostic, th...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) S. 8047 - 8057
Hauptverfasser:	Lang, Chunbo, Cheng, Gong, Tu, Binfei, Han, Junwei
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 01.06.2022
Schlagworte:	Adaptation models Computer vision grouping and shape analysis Image segmentation Performance gain Predictive models Semantics Sensitivity Transfer/low-shot/long-tail learning; Deep learning architectures and techniques; Segmentation
ISSN:	1063-6919
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!