Generative Models
PixelCNN
Introduced by Oord et al. in Pixel Recurrent Neural NetworksA PixelCNN is a generative model that uses autoregressive connections to model images pixel by pixel, decomposing the joint image distribution as a product of conditionals. PixelCNNs are much faster to train than PixelRNNs because convolutions are inherently easier to parallelize; given the vast number of pixels present in large image datasets this is an important advantage.
Source: Pixel Recurrent Neural Networks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Generation | 12 | 19.35% |
| Decoder | 6 | 9.68% |
| General Classification | 3 | 4.84% |
| Density Estimation | 3 | 4.84% |
| Semantic Segmentation | 2 | 3.23% |
| Image Inpainting | 2 | 3.23% |
| Atari Games | 2 | 3.23% |
| Video Generation | 2 | 3.23% |
| Adversarial Robustness | 2 | 3.23% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
