NAS-FPN is a Feature Pyramid Network that is discovered via Neural Architecture Search in a novel scalable search space covering all cross-scale connections. The discovered architecture consists of a combination of top-down and bottom-up connections to fuse features across scales
Source: NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object DetectionPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Object Detection | 9 | 29.03% |
Object | 5 | 16.13% |
Semantic Segmentation | 4 | 12.90% |
Instance Segmentation | 3 | 9.68% |
Image Augmentation | 2 | 6.45% |
Image Classification | 2 | 6.45% |
Real-Time Object Detection | 2 | 6.45% |
Real-Time Semantic Segmentation | 1 | 3.23% |
General Classification | 1 | 3.23% |
Component | Type |
|
---|---|---|
![]() |
Normalization | |
![]() |
Convolutions | |
![]() |
Pooling Operations | |
![]() |
Neural Architecture Search | |
![]() |
Activation Functions |