Generalizing Interactive Backpropagating Refinement for Dense Prediction Networks

As deep neural networks become the state-of-the-art approach in the field of computer vision for dense prediction tasks, many methods have been developed for automatic estimation of the target outputs given the visual inputs. Although the estimation accuracy of the proposed automatic methods continu...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) S. 763 - 772
Hauptverfasser:	Lin, Fanqing, Price, Brian, Martinez, Tony
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 01.06.2022
Schlagworte:	Computer vision Deep learning Deep learning architectures and techniques; Segmentation Estimation grouping and shape analysis; Vision applications and systems Image segmentation Semantics Shape Visualization
ISSN:	1063-6919
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!