Convolutions
Submanifold Convolution
Introduced by Graham et al. in 3D Semantic Segmentation with Submanifold Sparse Convolutional NetworksSubmanifold Convolution (SC) is a spatially sparse convolution operation used for tasks with sparse data like semantic segmentation of 3D point clouds. An SC convolution computes the set of active sites in the same way as a regular convolution: it looks for the presence of any active sites in its receptive field of size $f^{d}$. If the input has size $l$ then the output will have size $\left(l − f + s\right)/s$. Unlike a regular convolution, an SC convolution discards the ground state for non-active sites by assuming that the input from those sites is zero. For more details see the paper, or the official code here.
Source: 3D Semantic Segmentation with Submanifold Sparse Convolutional Networks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Semantic Segmentation | 4 | 23.53% |
| 3D Instance Segmentation | 2 | 11.76% |
| Clustering | 2 | 11.76% |
| Instance Segmentation | 2 | 11.76% |
| 3D Semantic Segmentation | 2 | 11.76% |
| Panoptic Segmentation | 1 | 5.88% |
| Scene Understanding | 1 | 5.88% |
| Multi-Task Learning | 1 | 5.88% |
| 4D Spatio Temporal Semantic Segmentation | 1 | 5.88% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
