Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection
Open paper
Benchmark
Model
Rank
Results
object-detection-on-lvis-v1-0-val
RichSem (Focal-H + ImageNet as weakly-supervised extra data)
#5
box AP: 61.2
box APr: 61.2
Rank counts only results with a code link.