mAP: 28.64±0.21
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
detector: FCOS-Res50
mAP: 29.12±0.2
mAP: 30.40
mAP: 29.11
mAP: 31.87
mAP: 32.23± 0.14
mAP: 31.5± 0.10
mAP: 24.85
mAP: 13.93
Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection
mAP: 30.7
mAP: 28.7
mAP: 34.04detector: FasterRCNN-Res50
mAP: 31.61
mAP: 32.166
mAP: 34.7
mAP: 23.2
mAP: 27.77
mAP: 27.70
mAP: 28.69±0.17
mAP: 33.53
mAP: 28.37±0.03