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 ResNet-50), 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 $IC(x,y,i,j) = max(0,1-|x-i|)\times max(0,1-|y-j|)$ 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 top-left and bottom-right points, respectively. We perform pooling (e.g. average pooling) given $bin$ and feature map $\mathcal{F}$ by computing a two-order integral:
Source: Acquisition of Localization Confidence for Accurate Object DetectionPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Object Detection | 2 | 25.00% |
Image-to-Image Translation | 1 | 12.50% |
Rgb-T Tracking | 1 | 12.50% |
Instance Segmentation | 1 | 12.50% |
Open-Ended Question Answering | 1 | 12.50% |
Semantic Segmentation | 1 | 12.50% |
General Classification | 1 | 12.50% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |