Grid Sensitive is a trick for object detection introduced by YOLOv4. When we decode the coordinate of the bounding box center $x$ and $y$, in original YOLOv3, we can get them by
$$ \begin{aligned} &x=s \cdot\left(g_{x}+\sigma\left(p_{x}\right)\right) \ &y=s \cdot\left(g_{y}+\sigma\left(p_{y}\right)\right) \end{aligned} $$
where $\sigma$ is the sigmoid function, $g_{x}$ and $g_{y}$ are integers and $s$ is a scale factor. Obviously, $x$ and $y$ cannot be exactly equal to $s \cdot g_{x}$ or $s \cdot\left(g_{x}+1\right)$. This makes it difficult to predict the centres of bounding boxes that just located on the grid boundary. We can address this problem, by changing the equation to
$$ \begin{aligned} &x=s \cdot\left(g_{x}+\alpha \cdot \sigma\left(p_{x}\right)(\alpha1) / 2\right) \ &y=s \cdot\left(g_{y}+\alpha \cdot \sigma\left(p_{y}\right)(\alpha1) / 2\right) \end{aligned} $$
This makes it easier for the model to predict bounding box center exactly located on the grid boundary. The FLOPs added by Grid Sensitive are really small, and can be totally ignored.
Source: YOLOv4: Optimal Speed and Accuracy of Object DetectionPaper  Code  Results  Date  Stars 

Task  Papers  Share 

Object Detection  29  35.80% 
RealTime Object Detection  6  7.41% 
Semantic Segmentation  5  6.17% 
Instance Segmentation  3  3.70% 
Autonomous Driving  3  3.70% 
License Plate Detection  2  2.47% 
Domain Adaptation  2  2.47% 
SelfDriving Cars  2  2.47% 
2D object detection  2  2.47% 
Component  Type 


🤖 No Components Found  You can add them if they exist; e.g. Mask RCNN uses RoIAlign 