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


Paper Code Results Date Stars


Task Papers Share
Image Super-Resolution 1 20.00%
Super-Resolution 1 20.00%
Camera Localization 1 20.00%
Scene Understanding 1 20.00%
Semantic Segmentation 1 20.00%


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