Viet-Anh on Software Logo

What is: Triplet Attention?

SourceRotate to Attend: Convolutional Triplet Attention Module
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

Triplet attention comprises of three branches each responsible for capturing crossdimension between the spatial dimensions and channel dimension of the input. Given an input tensor with shape (C × H × W), each branch is responsible for aggregating cross-dimensional interactive features between either the spatial dimension H or W and the channel dimension C.