Viet-Anh on Software Logo

What is: Squeeze aggregated excitation network?

SourceSqueeze aggregated excitation network
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

This method introduces the aggregated dense block within the squeeze excitation block to enhance representation. The squeeze method compresses the input flow and sends it to excitation with dense layers to regain its shape. The paper introduces multiple dense layers stacked side by side, similar to ResNeXt. This learns global representations from the condensed information which enhances the representational power of the network.