Bottleneck Transformer Block

2000년 도입 · 논문 10편에서 사용

A Bottleneck Transformer Block is a block used in Bottleneck Transformers that replaces the spatial 3 × 3 convolution layer in a Residual Block with Multi-Head Self-Attention (MHSA).

출처: Bottleneck Transformers for Visual Recognition

소개 논문: Bottleneck Transformers for Visual Recognition