Mask R-CNN + NL blocks (4 in head, 1 in backbone)

Reported on 3 benchmarks across 3 tasks · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision1 result

Pose EstimationonCOCO (Common Objects in Context)
Validation AP· 2017-11-21
66.5
best: 82.2 (Sapiens-2B)
SOTA
Non-local Neural Networks arXiv:1711.07971

Methodology1 result

3DonCOCO (Common Objects in Context)
Validation AP· 2017-11-21
66.5
best: 82.2 (Sapiens-2B)
SOTA
Non-local Neural Networks arXiv:1711.07971

Audio1 result

1 Image, 2*2 StitchionCOCO (Common Objects in Context)
Validation AP· 2017-11-21
66.5
best: 82.2 (Sapiens-2B)
SOTA
Non-local Neural Networks arXiv:1711.07971