RoI Feature Extractors

# Position-Sensitive RoI Pooling

Introduced by Dai et al. in R-FCN: Object Detection via Region-based Fully Convolutional Networks

Position-Sensitive RoI Pooling layer aggregates the outputs of the last convolutional layer and generates scores for each RoI. Unlike RoI Pooling, PS RoI Pooling conducts selective pooling, and each of the $k$ × $k$ bin aggregates responses from only one score map out of the bank of $k$ × $k$ score maps. With end-to-end training, this RoI layer shepherds the last convolutional layer to learn specialized position-sensitive score maps.

#### Papers

Paper Code Results Date Stars