YOLACT-550++ (ResNet-101-FPN)

Reported on 6 benchmarks across 1 task · 1 paper · 5 SOTA

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

Computer Vision6 results

Instance SegmentationonMSCOCO
AP50· 2019-12-03
53.8
best: 67.4 (RTMDet-Ins-x)
SOTA
YOLACT++: Better Real-time Instance Segmentation arXiv:1912.06218
Instance SegmentationonMSCOCO
AP75· 2019-12-03
36.9
best: 47.8 (RTMDet-Ins-x)
SOTA
YOLACT++: Better Real-time Instance Segmentation arXiv:1912.06218
Instance SegmentationonMSCOCO
APL· 2019-12-03
55.1
best: 65.5 (RTMDet-Ins-x)
SOTA
YOLACT++: Better Real-time Instance Segmentation arXiv:1912.06218
Instance SegmentationonMSCOCO
APM· 2019-12-03
36.8
best: 48 (RTMDet-Ins-l)
SOTA
YOLACT++: Better Real-time Instance Segmentation arXiv:1912.06218
Instance SegmentationonMSCOCO
mask AP· 2019-12-03
34.6
best: 44.6 (RTMDet-Ins-x)
SOTA
YOLACT++: Better Real-time Instance Segmentation arXiv:1912.06218
Instance SegmentationonMSCOCO
APS· 2019-12-03
11.9
best: 22.2 (RTMDet-Ins-x)
YOLACT++: Better Real-time Instance Segmentation arXiv:1912.06218