RoIAlign

2000년 도입 · 논문 611편에서 사용

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).

출처: Mask R-CNN

소개 논문: Mask R-CNN