Adaptive Feature Pooling pools features from all levels for each proposal in object detection and fuses them for the following prediction. For each proposal, we map them to different feature levels. Following the idea of Mask R-CNN, RoIAlign is used to pool feature grids from each level. Then a fusion operation (element-wise max or sum) is utilized to fuse feature grids from different levels.
The motivation for this technique is that in an FPN we assign proposals to different feature levels based on the size of proposals, which could be suboptimal if images with small differences are assigned to different levels, or if the importance of features is not strongly correlated to their level which they belong.
Source: Path Aggregation Network for Instance SegmentationPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Object Detection | 4 | 16.67% |
Semantic Segmentation | 3 | 12.50% |
Real-Time Object Detection | 2 | 8.33% |
Instance Segmentation | 2 | 8.33% |
Face Sketch Synthesis | 1 | 4.17% |
Crowd Counting | 1 | 4.17% |
Anatomy | 1 | 4.17% |
Vehicle Re-Identification | 1 | 4.17% |
Demosaicking | 1 | 4.17% |