Mixture model network

Introduced by Monti et al. in Geometric deep learning on graphs and manifolds using mixture model CNNs

Mixture model network (MoNet) is a general framework allowing to design convolutional deep architectures on non-Euclidean domains such as graphs and manifolds.

Image and description from: Geometric deep learning on graphs and manifolds using mixture model CNNs

Source: Geometric deep learning on graphs and manifolds using mixture model CNNs

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Semantic Segmentation	3	6.67%
Optical Flow Estimation	3	6.67%
Recommendation Systems	2	4.44%
Object Detection	2	4.44%
Image Generation	2	4.44%
Object Discovery	2	4.44%
Unsupervised Object Segmentation	2	4.44%
Autonomous Navigation	1	2.22%
Decision Making	1	2.22%

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

Graph Models