Mask R-CNN+COCO

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.

Medical1 result

Semantic SegmentationonCityscapes val
PQth· 2017-03-20
54
best: 64.6 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
SOTA
Mask R-CNN arXiv:1703.06870

Audio1 result

10-shot image generationonCityscapes val
PQth· 2017-03-20
54
best: 64.6 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
SOTA
Mask R-CNN arXiv:1703.06870

Computer Vision1 result

Panoptic SegmentationonCityscapes val
PQth· 2017-03-20
54
best: 64.6 (OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained))
SOTA
Mask R-CNN arXiv:1703.06870