Masked Convolution

2000년 도입 · 논문 26편에서 사용

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.

출처: Pixel Recurrent Neural Networks

소개 논문: Pixel Recurrent Neural Networks