Feature Fusion Module v2 is a feature fusion module from the M2Det object detection model, and is crucial for constructing the final multi-level feature pyramid. They use 1x1 convolution layers to compress the channels of the input features and use a concatenation operation to aggregate these feature map. FFMv2 takes the base feature and the largest output feature map of the previous Thinned U-Shape Module (TUM) – these two are of the same scale – as input, and produces the fused feature for the next TUM.
Source: M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid NetworkPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
3D Feature Matching | 1 | 20.00% |
document understanding | 1 | 20.00% |
Text Detection | 1 | 20.00% |
Text Spotting | 1 | 20.00% |
Object Detection | 1 | 20.00% |