Viet-Anh on Software Logo

What is: Selective Kernel Convolution?

SourceSelective Kernel Networks
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

A Selective Kernel Convolution is a convolution that enables neurons to adaptively adjust their RF sizes among multiple kernels with different kernel sizes. Specifically, the SK convolution has three operators – Split, Fuse and Select. Multiple branches with different kernel sizes are fused using softmax attention that is guided by the information in these branches. Different attentions on these branches yield different sizes of the effective receptive fields of neurons in the fusion layer