Convolutions
Depthwise Convolution
Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D convolution performed over multiple input channels, the filter is as deep as the input and lets us freely mix channels to generate each element in the output. In contrast, depthwise convolutions keep each channel separate. To summarize the steps, we:
- Split the input and filter into channels.
- We convolve each input with the respective filter.
- We stack the convolved outputs together.
Image Credit: Chi-Feng Wang
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 71 | 10.74% |
| Object Detection | 49 | 7.41% |
| Semantic Segmentation | 37 | 5.60% |
| Classification | 34 | 5.14% |
| Quantization | 31 | 4.69% |
| Instance Segmentation | 10 | 1.51% |
| Computational Efficiency | 10 | 1.51% |
| Image Segmentation | 9 | 1.36% |
| Management | 9 | 1.36% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
