SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation

This paper studies a practical domain adaptive (DA) semantic segmentation problem where only pseudo-labeled target data is accessible through a black-box model. Due to the domain gap and label shift between two domains, pseudo-labeled target data contains mixed closed-set and open-set label noises....

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) S. 7022 - 7031
Hauptverfasser:	Guo, Xiaoqing, Liu, Jie, Liu, Tongliang, Yuan, Yixuan
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 01.06.2022
Schlagworte:	Adaptation models Computational geometry Computational modeling Estimation grouping and shape analysis Representation learning Semantics Solid modeling Transfer/low-shot/long-tail learning; Deep learning architectures and techniques; Scene analysis and understanding; Segmentation
ISSN:	1063-6919
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!