Grid R-CNN is an object detection framework, where the traditional regression formulation is replaced by a grid point guided localization mechanism.
Grid R-CNN divides the object bounding box region into grids and employs a fully convolutional network (FCN) to predict the locations of grid points. Owing to the position sensitive property of fully convolutional architecture, Grid R-CNN maintains the explicit spatial information and grid points locations can be obtained in pixel level. When a certain number of grid points at specified location are known, the corresponding bounding box is definitely determined. Guided by the grid points, Grid R-CNN can determine more accurate object bounding box than regression method which lacks the guidance of explicit spatial information.
Source: Grid R-CNNPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Object Detection | 3 | 50.00% |
2D Object Detection | 1 | 16.67% |
Novel Object Detection | 1 | 16.67% |
Object Localization | 1 | 16.67% |
Component | Type |
|
---|---|---|
Convolution
|
Convolutions | |
Dilated Convolution
|
Convolutions | |
FCN
|
Semantic Segmentation Models | |
RoIAlign
|
RoI Feature Extractors | |
RPN
|
Region Proposal | |
Sigmoid Activation
|
Activation Functions |