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...

Full description

Bibliographic Details

Published in:	Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 4763 - 4772
Main Authors:	Nguyen, Duy-Kien, Ju, Jihong, Booij, Olaf, Oswald, Martin R., Snoek, Cees G. M.
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.06.2022
Subjects:	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 Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!