RoI Feature Extractors


Introduced by He et al. in Mask R-CNN

Region of Interest Align, or RoIAlign, is an operation for extracting a small feature map from each RoI in detection and segmentation based tasks. It removes the harsh quantization of RoI Pool, properly aligning the extracted features with the input. To avoid any quantization of the RoI boundaries or bins (using $x/16$ instead of $[x/16]$), RoIAlign uses bilinear interpolation to compute the exact values of the input features at four regularly sampled locations in each RoI bin, and the result is then aggregated (using max or average).

Source: Mask R-CNN


Paper Code Results Date Stars


Task Papers Share
Semantic Segmentation 191 16.90%
Instance Segmentation 170 15.04%
Object Detection 144 12.74%
Image Classification 25 2.21%
General Classification 19 1.68%
Classification 15 1.33%
Panoptic Segmentation 15 1.33%
Image Segmentation 14 1.24%
Pose Estimation 13 1.15%


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