computer-vision-4
Semi-Supervised Object Detection
3260 papers • 126 benchmarks • 313 datasets
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.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in semi-supervised-object-detection-4
Trend
Dataset
Best Model
Actions
COCO 10% labeled data
COCO 10% labeled data
COCO 5% labeled data
COCO 5% labeled data
Libraries
iUse these libraries to find semi-supervised-object-detection-4 models and implementations
4 papers 136
Datasets
Subtasks
No subtasks available.
Most implemented papers
End-to-End Semi-Supervised Object Detection with Soft Teacher
Zicheng Liu, Lijuan Wang, Han Hu, X. Bai, Zheng Zhang, Fangyun Wei, Mengde Xu, Jianfeng Wang•Tue Jun 15 2021
This paper presents an end-to-end semi-supervised object detection approach, in contrast to previous more complex multi-stage methods, and proposes two simple yet effective techniques within this framework: a soft teacher mechanism where the classification loss of each unlabeled bounding box is weighed by the classification score produced by the teacher network.
