Bottleneck Transformers for Visual Recognition

Aravind Srinivas
Aravind Srinivas
Niki Parmar
Niki Parmar

CVPR, pp. 16519-16529, 2021.

Cited by: 1|Views72
EI

Abstract:

We present BoTNet, a conceptually simple yet powerful backbone architecture that incorporates self-attention for multiple computer vision tasks including image classification, object detection and instance segmentation. By just replacing the spatial convolutions with global self-attention in the final three bottleneck blocks of a ResNet...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments