Methods > Computer Vision > Image Models

Self-Attention Network

Introduced by Zhao et al. in Exploring Self-attention for Image Recognition

Self-Attention Network (SANet) proposes two variations of self-attention used for image recognition: 1) pairwise self-attention which generalizes standard dot-product attention and is fundamentally a set operator, and 2) patchwise self-attention which is strictly more powerful than convolution.

Source: Exploring Self-attention for Image Recognition

Latest Papers

PAPER DATE
Learning Camera Localization via Dense Scene Matching
| Shitao TangChengzhou TangRui HuangSiyu ZhuPing Tan
2021-03-31
SaNet: Scale-aware Neural Network for Semantic Labelling of Multiple Spatial Resolution Aerial Images
Libo WangShenghui FangCe ZhangRui LiChenxi DuanXiaoliang MengPeter M. Atkinson
2021-03-14
Exploring Self-attention for Image Recognition
| Hengshuang ZhaoJiaya JiaVladlen Koltun
2020-04-28

Tasks

TASK PAPERS SHARE
Camera Localization 1 33.33%
Scene Understanding 1 33.33%
Semantic Segmentation 1 33.33%

Components

COMPONENT TYPE
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories