Convolutions
Masked Convolution
Introduced by Oord et al. in Pixel Recurrent Neural NetworksA 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
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Semantic Segmentation | 3 | 5.26% |
| Time Series Prediction | 3 | 5.26% |
| Decoder | 3 | 5.26% |
| Decision Making | 2 | 3.51% |
| quantile regression | 2 | 3.51% |
| regression | 2 | 3.51% |
| Benchmarking | 2 | 3.51% |
| Object Detection | 2 | 3.51% |
| Quantum Machine Learning | 2 | 3.51% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
