ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition
Open paper
Benchmark
Model
Rank
Results
human-pose-keypoint-estimation-on-coco-test-dev
HigherHRNet (ScaleNet_P4)
–
AP: 71.6
AP50: 90.3
AP75: 78.2
AR: 76.0
AR50: 92.3
multi-person-pose-estimation-on-crowdpose
HigherHRNet (ScaleNet_P4)
–
mAP @0.5:0.95: 71.3
Rank counts only results with a code link.