RoI Feature Extractors
RoIPool
Introduced by Girshick et al. in Rich feature hierarchies for accurate object detection and semantic segmentationRegion of Interest Pooling, or RoIPool, is an operation for extracting a small feature map (e.g., $7×7$) from each RoI in detection and segmentation based tasks. Features are extracted from each candidate box, and thereafter in models like Fast R-CNN, are then classified and bounding box regression performed.
The actual scaling to, e.g., $7×7$, occurs by dividing the region proposal into equally sized sections, finding the largest value in each section, and then copying these max values to the output buffer. In essence, RoIPool is max pooling on a discrete grid based on a box.
Image Source: Joyce Xu
Source: Rich feature hierarchies for accurate object detection and semantic segmentation
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 283 | 30.59% |
| Semantic Segmentation | 35 | 3.78% |
| Image Classification | 32 | 3.46% |
| Instance Segmentation | 27 | 2.92% |
| General Classification | 23 | 2.49% |
| Autonomous Driving | 16 | 1.73% |
| Classification | 14 | 1.51% |
| Pedestrian Detection | 14 | 1.51% |
| Domain Adaptation | 14 | 1.51% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
