Viet-Anh on Software Logo

What is: Masked Convolution?

SourcePixel Recurrent Neural Networks
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

A Masked Convolution is a type of convolution which masks certain pixels so that the model can only predict based on pixels already seen. This type of convolution was introduced with PixelRNN generative models, where an image is generated pixel by pixel, to ensure that the model was conditional only on pixels already visited.