从RoI Pooling 到 RoI Align -- Mask R-CNN 论文思想解析

RoIAlign: RoIPool [12] is a standard operation for extracting a small feature map (e.g., 7×7) from each RoI. RoIPool first quantizes a floating-number RoI to the discrete granularity of the feature map, this quantized RoI is then subdivided into spatial bins which are themselves quantized, and finally feature values covered by each bin are aggregated (usually by max pooling). Quantization is performed, e.g., on a continuous coordinate x by computing [x/16], where 16 is a feature map stride and [·] is rounding; likewise, quantization is performed whe