Precise RoI Pooling, or PrRoI Pooling, is a region of interest feature extractor that avoids any quantization of coordinates and has a continuous gradient on bounding box coordinates. Given the feature map $\mathcal{F}$ before RoI/PrRoI Pooling (eg from Conv4 in ResNet50), let $w_{i,j}$ be the feature at one discrete location $(i,j)$ on the feature map. Using bilinear interpolation, the discrete feature map can be considered continuous at any continuous coordinates $(x,y)$:
$$ f(x,y) = \sum_{i,j}IC(x,y,i,j) \times w_{i,j}, $$
where $IC(x,y,i,j) = max(0,1xi)\times max(0,1yj)$ is the interpolation coefficient. Then denote a bin of a RoI as $bin={(x_1,y_1),(x_2,y_2)}$, where $(x_1,y_1)$ and $(x_2,y_2)$ are the continuous coordinates of the topleft and bottomright points, respectively. We perform pooling (e.g. average pooling) given $bin$ and feature map $\mathcal{F}$ by computing a twoorder integral:
Source: Acquisition of Localization Confidence for Accurate Object DetectionPaper  Code  Results  Date  Stars 

Task  Papers  Share 

Object Detection  2  28.57% 
ImagetoImage Translation  1  14.29% 
RgbT Tracking  1  14.29% 
Instance Segmentation  1  14.29% 
Semantic Segmentation  1  14.29% 
General Classification  1  14.29% 
Component  Type 


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