Mask Scoring R-CNN

1 Mar 2019Zhaojin Huang • Lichao Huang • Yongchao Gong • Chang Huang • Xinggang Wang

In the task of instance segmentation, the confidence of instance classification is used as mask quality score in most instance segmentation frameworks. In this paper, we study this problem and propose Mask Scoring R-CNN which contains a network block to learn the quality of the predicted instance masks. The mask scoring strategy calibrates the misalignment between mask quality and mask score, and improves instance segmentation performance by prioritizing more accurate mask predictions during COCO AP evaluation.

PDF Abstract

Evaluation


Task Dataset Model Metric name Metric value Global rank Compare
Instance Segmentation COCO MS R-CNN + ResNet-101 DCN + FPN Average Precision 39.6% # 3