Mask Scoring R-CNN

Zhaojin HuangLichao HuangYongchao GongChang HuangXinggang Wang

   Papers with code   Abstract  PDF

Letting a deep network be aware of the quality of its own predictions is an interesting yet important problem. In the task of instance segmentation, the confidence of instance classification is used as mask quality score in most instance segmentation frameworks... (read more)

Benchmarked Models

RANK
MODEL
REPO
CODE RESULT
PAPER RESULT
ε-REPRODUCED
BUILD
1
Mask Scoring R-CNN
(ResNeXt-101 64x4d-FPN…)
0.422
--
2
Mask Scoring R-CNN
(ResNeXt-101 64x4d-FPN…)
0.420
--
3
Mask Scoring R-CNN
(ResNet-101-FPN, LR 2x)
0.407
--
4
Mask Scoring R-CNN
(ResNet-101-FPN, LR 1x)
0.398
--
5
Mask Scoring R-CNN
(ResNet-50-FPN, LR 2x)
0.382
--
6
Mask Scoring R-CNN
(ResNet-50-FPN, LR 1x)
0.374
--