mAP: 21.88
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: 23.86
mAP: 20.75± 0.12
mAP: 13.97±0.35
mAP: 19.47
mAP: 14.58 ± 0.3
mAP: 23.76
mAP: 20.46
mAP: 18.05
mAP: 23.55±0.25
mAP: 23.83
mAP: 18.6
mAP: 22.43
mAP: 19.02 ± 0.25
mAP: 19.62±0.37
mAP: 21.63
mAP: 21.26 ± 0.21