An Recursive Feature Pyramid (RFP) builds on top of the Feature Pyramid Networks (FPN) by incorporating extra feedback connections from the FPN layers into the bottom-up backbone layers. Unrolling the recursive structure to a sequential implementation, we obtain a backbone for object detector that looks at the images twice or more. Similar to the cascaded detector heads in Cascade R-CNN trained with more selective examples, an RFP recursively enhances FPN to generate increasingly powerful representations. Resembling Deeply-Supervised Nets, the feedback connections bring the features that directly receive gradients from the detector heads back to the low levels of the bottom-up backbone to speed up training and boost performance.
Source: DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous ConvolutionPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Object | 2 | 13.33% |
Semantic Segmentation | 2 | 13.33% |
Graph Classification | 1 | 6.67% |
Node Classification | 1 | 6.67% |
3D Object Editing | 1 | 6.67% |
Scene Segmentation | 1 | 6.67% |
Time Series Analysis | 1 | 6.67% |
Automatic Speech Recognition (ASR) | 1 | 6.67% |
Speech Recognition | 1 | 6.67% |