Semi Supervised Object Detection On Coco 1

Métriques

mAP

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	mAP	Paper Title	Repository
MixTeacher-FRCNN	25.16	MixTeacher: Mining Promising Labels with Mixed Scale Teacher for Semi-Supervised Object Detection
PseCo	22.43	PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection
Efficient Teacher	23.76	Efficient Teacher: Semi-Supervised Object Detection for YOLOv5
MixPL	31.7	Mixed Pseudo Labels for Semi-Supervised Object Detection
Omni-DETR	18.6	Omni-DETR: Omni-Supervised Object Detection with Transformers
VC	23.86	Semi-supervised Object Detection via Virtual Category Learning
SSOD with OCL and RUPL	21.63	Semi-Supervised Object Detection with Object-wise Contrastive Learning and Regression Uncertainty	-
Unbiased Teacher v2	26.07±0.36	Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors
Soft Teacher + Swin-L(HTC++, multi-scale)	20.46	End-to-End Semi-Supervised Object Detection with Soft Teacher
MUM	21.88	MUM : Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection
ARSL	25.36	Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection
DETReg	14.58 ± 0.3	DETReg: Unsupervised Pretraining with Region Priors for Object Detection
STAC	13.97±0.35	A Simple Semi-Supervised Learning Framework for Object Detection
RPL	19.02 ± 0.25	Rethinking Pseudo Labels for Semi-Supervised Object Detection	-
Consistent-Teacher	25.5	Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection
ASTOD	19.47	Adaptive Self-Training for Object Detection
Unbiased Teacher	20.75± 0.12	Unbiased Teacher for Semi-Supervised Object Detection
Instant Teaching	18.05	Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework
Adaptive Class-Rebalancing	26.07±0.46	Semi-Supervised Object Detection with Adaptive Class-Rebalancing Self-Training	-
Semi-DETR	30.50±0.30	Semi-DETR: Semi-Supervised Object Detection with Detection Transformers

0 of 22 row(s) selected.