RoIPool

Introduced by Girshick et al. in Rich feature hierarchies for accurate object detection and semantic segmentation

Region of Interest Pooling, or RoIPool, is an operation for extracting a small feature map (e.g., $7×7$) from each RoI in detection and segmentation based tasks. Features are extracted from each candidate box, and thereafter in models like Fast R-CNN, are then classified and bounding box regression performed.

The actual scaling to, e.g., $7×7$, occurs by dividing the region proposal into equally sized sections, finding the largest value in each section, and then copying these max values to the output buffer. In essence, RoIPool is max pooling on a discrete grid based on a box.

Image Source: Joyce Xu

Source: Rich feature hierarchies for accurate object detection and semantic segmentation

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Object Detection	277	24.78%
Object	154	13.77%
Semantic Segmentation	33	2.95%
Image Classification	29	2.59%
Instance Segmentation	27	2.42%
General Classification	20	1.79%
Autonomous Driving	18	1.61%
Domain Adaptation	14	1.25%
Classification	13	1.16%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
🤖 No Components Found	You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories

Add Remove

RoI Feature Extractors