Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks
00x1
论文标题:Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks
来源:清华大学Jittor
00x2
文章重点通过引入external attention来代替self-attention,并且external attention能够贯穿所有样本,学习到所有样本共享的特征。为此,我们需要引入一个外部的SxD的记忆单元M。
They(two memories)are inde.
原创
2021-05-14 10:35:37 ·
714 阅读 ·
1 评论