RoI Feature Extractors
RoIAlign
Introduced by He et al. in Mask R-CNNRegion of Interest Align, or RoIAlign, is an operation for extracting a small feature map from each RoI in detection and segmentation based tasks. It removes the harsh quantization of RoI Pool, properly aligning the extracted features with the input. To avoid any quantization of the RoI boundaries or bins (using $x/16$ instead of $[x/16]$), RoIAlign uses bilinear interpolation to compute the exact values of the input features at four regularly sampled locations in each RoI bin, and the result is then aggregated (using max or average).
Source: Mask R-CNN
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Semantic Segmentation | 173 | 14.30% |
| Instance Segmentation | 153 | 12.64% |
| Object Detection | 126 | 10.41% |
| Object | 68 | 5.62% |
| Image Classification | 23 | 1.90% |
| Classification | 18 | 1.49% |
| Text Classification | 17 | 1.40% |
| Image Segmentation | 15 | 1.24% |
| Panoptic Segmentation | 14 | 1.16% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
