HyperAIHyperAI

Semi Supervised Object Detection On Coco 1

Metrics

mAP

Results

Performance results of various models on this benchmark

Model Name
mAP
Paper TitleRepository
MixTeacher-FRCNN25.16MixTeacher: Mining Promising Labels with Mixed Scale Teacher for Semi-Supervised Object Detection-
PseCo22.43PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection-
Efficient Teacher23.76Efficient Teacher: Semi-Supervised Object Detection for YOLOv5-
MixPL31.7Mixed Pseudo Labels for Semi-Supervised Object Detection-
Omni-DETR18.6Omni-DETR: Omni-Supervised Object Detection with Transformers-
VC23.86Semi-supervised Object Detection via Virtual Category Learning-
SSOD with OCL and RUPL21.63Semi-Supervised Object Detection with Object-wise Contrastive Learning and Regression Uncertainty-
Unbiased Teacher v226.07±0.36Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors-
Soft Teacher + Swin-L(HTC++, multi-scale)20.46End-to-End Semi-Supervised Object Detection with Soft Teacher-
MUM21.88MUM : Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection-
ARSL25.36Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection-
DETReg14.58 ± 0.3DETReg: Unsupervised Pretraining with Region Priors for Object Detection-
STAC13.97±0.35A Simple Semi-Supervised Learning Framework for Object Detection-
RPL19.02 ± 0.25Rethinking Pseudo Labels for Semi-Supervised Object Detection-
Consistent-Teacher25.5Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection-
ASTOD19.47Adaptive Self-Training for Object Detection-
Unbiased Teacher20.75± 0.12Unbiased Teacher for Semi-Supervised Object Detection-
Instant Teaching18.05Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework-
Adaptive Class-Rebalancing26.07±0.46Semi-Supervised Object Detection with Adaptive Class-Rebalancing Self-Training-
Semi-DETR30.50±0.30Semi-DETR: Semi-Supervised Object Detection with Detection Transformers-
0 of 22 row(s) selected.