Masked AutoDecoder is Effective Multi-Task Vision Generalist
Open paper
Benchmark
Model
Rank
Results
human-pose-keypoint-estimation-on-coco-val2017
MAD (ViT-B)
#102
AP: 66.5
object-detection-on-coco-val2017
MAD (ViT-B)
#216
box AP: 50.1
Rank counts only results with a code link.