A Panoptic FPN is an extension of an FPN that can generate both instance and semantic segmentations via FPN. The approach starts with an FPN backbone and adds a branch for performing semantic segmentation in parallel with the existing region-based branch for instance segmentation. No changes are made to the FPN backbone when adding the dense-prediction branch, making it compatible with existing instance segmentation methods.
The new semantic segmentation branch achieves its goal as follows. Starting from the deepest FPN level (at 1/32 scale), we perform three upsampling stages to yield a feature map at 1/4 scale, where each upsampling stage consists of 3×3 convolution, group norm, ReLU, and 2× bilinear upsampling. This strategy is repeated for FPN scales 1/16, 1/8, and 1/4 (with progressively fewer upsampling stages). The result is a set of feature maps at the same 1/4 scale, which are then element-wise summed. A final 1×1 convolution, 4× bilinear upsampling, and softmax are used to generate the per-pixel class labels at the original image resolution. In addition to stuff classes, this branch also outputs a special ‘other’ class for all pixels belonging to objects (to avoid predicting stuff classes for such pixels).
Source: Panoptic Feature Pyramid NetworksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Instance Segmentation | 3 | 30.00% |
Semantic Segmentation | 3 | 30.00% |
Image Segmentation | 1 | 10.00% |
Scene Segmentation | 1 | 10.00% |
Panoptic Segmentation | 1 | 10.00% |
Thermal Image Segmentation | 1 | 10.00% |
Component | Type |
|
---|---|---|
1x1 Convolution
|
Convolutions | |
Convolution
|
Convolutions | |
FPN
|
Feature Extractors | |
Group Normalization
|
Normalization | |
ReLU
|
Activation Functions | |
Softmax
|
Output Functions |