Masked Convolution

Introduced by Oord et al. in Pixel Recurrent Neural Networks

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.

Source: Pixel Recurrent Neural Networks

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Machine Translation	2	12.50%
Language Modelling	2	12.50%
Sentiment Analysis	2	12.50%
Image Generation	2	12.50%
Image Classification	1	6.25%
Object Detection	1	6.25%
Semantic Segmentation	1	6.25%
Image Inpainting	1	6.25%
General Classification	1	6.25%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
🤖 No Components Found	You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories

Add Remove

Convolutions