Weakly Supervised Instance Segmentation by Deep Community Learning
Open paper
Benchmark
Model
Rank
Results
image-level-supervised-instance-segmentation
CL
–
mAP@0.5: 38.1
mAP@0.25: 56.6
mAP@0.75: 12.3
weakly-supervised-instance-segmentation-on
WSIS_CL
–
Average Best Overlap: 48.2
mAP@0.25: 56.6
mAP@0.5: 38.1
…
Rank counts only results with a code link.