BoxeR: Box-Attention for 2D and 3D Transformers

In this paper, we propose a simple attention mechanism, we call Box-Attention. It enables spatial interaction between grid features, as sampled from boxes of interest, and improves the learning capability of transformers for several vision tasks. Specifically, we present BoxeR, short for Box Transfo...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) S. 4763 - 4772
Hauptverfasser:	Nguyen, Duy-Kien, Ju, Jihong, Booij, Olaf, Oswald, Martin R., Snoek, Cees G. M.
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 01.06.2022
Schlagworte:	categorization Codes Computer vision grouping and shape analysis Object detection Pattern recognition Recognition: detection retrieval; Deep learning architectures and techniques; Segmentation Task analysis Three-dimensional displays Transformers
ISSN:	1063-6919
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!