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 CNNsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Optical Flow Estimation | 3 | 7.89% |
Object Detection | 2 | 5.26% |
Image Generation | 2 | 5.26% |
Object Discovery | 2 | 5.26% |
Semantic Segmentation | 2 | 5.26% |
Unsupervised Object Segmentation | 2 | 5.26% |
Dialogue State Tracking | 1 | 2.63% |
Action Unit Detection | 1 | 2.63% |
Facial Action Unit Detection | 1 | 2.63% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |