Semi Supervised Object Detection On Coco 5

Métriques

mAP

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	mAP	Paper Title	Repository
Adaptive Class-Rebalancing	31.35±0.13	Semi-Supervised Object Detection with Adaptive Class-Rebalancing Self-Training	-
ASTOD	30.43	Adaptive Self-Training for Object Detection
PseCo	32.5	PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection
Omni-DETR	30.2	Omni-DETR: Omni-Supervised Object Detection with Transformers
Semi-DETR	40.1	Semi-DETR: Semi-Supervised Object Detection with Detection Transformers
DETReg	24.80±0.2	DETReg: Unsupervised Pretraining with Region Priors for Object Detection
MixPL	40.1	Mixed Pseudo Labels for Semi-Supervised Object Detection
Polishing Teacher	32.10±0.15	Mind the Gap: Polishing Pseudo labels for Accurate Semi-supervised Object Detection
Revisiting Class Imbalance	32.21	Revisiting Class Imbalance for End-to-end Semi-Supervised Object Detection	-
Dense Teacher	33.01	Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection
MixTeacher-FCOS	33.42	MixTeacher: Mining Promising Labels with Mixed Scale Teacher for Semi-Supervised Object Detection
ARSL	34.45	Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection
MUM	28.52	MUM : Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection
Unbiased Teacher v2	31.85±0.09	Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors
Unbiased Teacher	28.27± 0.11	Unbiased Teacher for Semi-Supervised Object Detection
MixTeacher-FRCNN	34.06	MixTeacher: Mining Promising Labels with Mixed Scale Teacher for Semi-Supervised Object Detection
Efficient Teacher	34.11	Efficient Teacher: Semi-Supervised Object Detection for YOLOv5
RPL	28.4 ± 0.15	Rethinking Pseudo Labels for Semi-Supervised Object Detection	-
STAC	24.38±0.12	A Simple Semi-Supervised Learning Framework for Object Detection
VC	32.05	Semi-supervised Object Detection via Virtual Category Learning

0 of 23 row(s) selected.