Deformable Position-Sensitive RoI Pooling

2000년 도입 · 논문 1편에서 사용

Deformable Position-Sensitive RoI Pooling is similar to PS RoI Pooling but it adds an offset to each bin position in the regular bin partition. Offset learning follows the “fully convolutional” spirit. In the top branch, a convolutional layer generates the full spatial resolution offset fields. For each RoI (also for each class), PS RoI pooling is applied on such fields to obtain normalized offsets, which are then transformed to the real offsets, in the same way as in deformable RoI pooling.

출처: Deformable Convolutional Networks

소개 논문: Deformable Convolutional Networks