Convolutions
CoordConv
Introduced by Liu et al. in An Intriguing Failing of Convolutional Neural Networks and the CoordConv SolutionA CoordConv layer is a simple extension to the standard convolutional layer. It has the same functional signature as a convolutional layer, but accomplishes the mapping by first concatenating extra channels to the incoming representation. These channels contain hard-coded coordinates, the most basic version of which is one channel for the $i$ coordinate and one for the $j$ coordinate.
The CoordConv layer keeps the properties of few parameters and efficient computation from convolutions, but allows the network to learn to keep or to discard translation invariance as is needed for the task being learned. This is useful for coordinate transform based tasks where regular convolutions can fail.
Source: An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 5 | 16.13% |
| Face Alignment | 3 | 9.68% |
| Real-Time Object Detection | 2 | 6.45% |
| Semantic Segmentation | 2 | 6.45% |
| Domain Adaptation | 1 | 3.23% |
| 2D Object Detection | 1 | 3.23% |
| Dense Object Detection | 1 | 3.23% |
| Multi-Object Tracking | 1 | 3.23% |
| Multiple Object Tracking | 1 | 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 |
