Diffusion-convolutional neural networks (DCNN) is a model for graph-structured data. Through the introduction of a diffusion-convolution operation, diffusion-based representations can be learned from graph structured data and used as an effective basis for node classification.
Description and image from: Diffusion-Convolutional Neural Networks
Source: Diffusion-Convolutional Neural NetworksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
General Classification | 42 | 9.61% |
Semantic Segmentation | 34 | 7.78% |
Image Classification | 29 | 6.64% |
Classification | 27 | 6.18% |
Object Recognition | 18 | 4.12% |
Image Segmentation | 15 | 3.43% |
Object Detection | 12 | 2.75% |
Face Recognition | 7 | 1.60% |
Face Verification | 5 | 1.14% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |