Attention Augmented Convolutional Networks

Irwan Bello
Irwan Bello
Barret Zoph
Barret Zoph

International Conference on Computer Vision, pp. 3286-3295, 2019.

Cited by: 51|Bibtex|Views115
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Convolutional networks have been the paradigm of choice in many computer vision applications. The convolution operation however has a significant weakness in that it only operates on a local neighborhood, thus missing global information. Self-attention, on the other hand, has emerged as a recent advance to capture long range interactions,...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments