Semi-Supervised Object Detection

8 benchmarks115 papers

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.

Benchmarks

Semi-Supervised Object Detection on COCO 10% labeled data

mAPdetector

Semi-Supervised Object Detection on COCO 5% labeled data

mAP

Semi-Supervised Object Detection on COCO 1% labeled data

mAP

Semi-Supervised Object Detection on COCO 100% labeled data

mAP

Semi-Supervised Object Detection on COCO 2% labeled data

mAP

Semi-Supervised Object Detection on COCO 0.5% labeled data

mAP

Semi-Supervised Object Detection on COCO

10%