Viet-Anh on Software Logo

What is: 1x1 Convolution?

SourceNetwork In Network
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction, efficient low dimensional embeddings, and applying non-linearity after convolutions. It maps an input pixel with all its channels to an output pixel which can be squeezed to a desired output depth. It can be viewed as an MLP looking at a particular pixel location.

Image Credit: http://deeplearning.ai