mAP: 34.06
Papers with Code · CC BY-SA 4.0
Semi-Supervised Object Detection
Semi-supervised object detection uses both labeled data and unlabeled data for training. It not only reduces the annotation burden for training high-performance object detectors but also further improves the object detector by using a large number of unlabeled data.
논문
mAP: 34.45
mAP: 40.1
mAP: 40.1
mAP: 31.35±0.13
mAP: 31.85±0.09
mAP: 24.38±0.12
mAP: 30.43
Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection
mAP: 25.5
mAP: 33.01
mAP: 24.80±0.2
mAP: 34.11
mAP: 30.74
mAP: 26.75
mAP: 32.10±0.15
mAP: 28.52
mAP: 30.2
mAP: 32.5
mAP: 28.4 ± 0.15
mAP: 32.21
mAP: 32.05
mAP: 30.66
mAP: 28.27± 0.11