R50-FPN-MaskRCNN-EQLv2

Reported on 1 benchmark across 1 task · 1 paper

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

Computer Vision1 result

Instance SegmentationonLVIS v1.0 val
mask AP· 2020-12-15
23.7
best: 60.7 (Co-DETR (single-scale))
Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection arXiv:2012.08548