SANet

2000년 도입 · 논문 11편에서 사용

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.

출처: Exploring Self-attention for Image Recognition

소개 논문: Exploring Self-attention for Image Recognition