AICurious Logo

What is: Selective Kernel?

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

A Selective Kernel unit is a bottleneck block consisting of a sequence of 1×1 convolution, SK convolution and 1×1 convolution. It was proposed as part of the SKNet CNN architecture. In general, all the large kernel convolutions in the original bottleneck blocks in ResNeXt are replaced by the proposed SK convolutions, enabling the network to choose appropriate receptive field sizes in an adaptive manner.

In SK units, there are three important hyper-parameters which determine the final settings of SK convolutions: the number of paths MM that determines the number of choices of different kernels to be aggregated, the group number GG that controls the cardinality of each path, and the reduction ratio rr that controls the number of parameters in the fuse operator. One typical setting of SK convolutions is SK[M,G,r]\text{SK}\left[M, G, r\right] to be SK[2,32,16]\text{SK}\left[2, 32, 16\right].