SOTAVerified

Semi-Supervised Object Detection

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.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 115 papers

TitleStatusHype
Building Blocks for Robust and Effective Semi-Supervised Real-World Object Detection—0
ClipGrader: Leveraging Vision-Language Models for Robust Label Quality Assessment in Object Detection—0
Semi-Supervised Weed Detection in Vegetable Fields: In-domain and Cross-domain Experiments—0
SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object DetectionCode1
Co-Learning: Towards Semi-Supervised Object Detection with Road-side Cameras—0
Collaborative Feature-Logits Contrastive Learning for Open-Set Semi-Supervised Object Detection—0
Applying the Lower-Biased Teacher Model in Semi-Supervised Object Detection—0
Semi-Supervised 3D Object Detection with Channel Augmentation using Transformation Equivariance—0
Class-balanced Open-set Semi-supervised Object Detection for Medical Images—0
Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer—0
Show:102550
← PrevPage 1 of 12Next →
All datasetsCOCO 10% labeled dataCOCO 5% labeled dataCOCO 1% labeled dataCOCO 100% labeled dataCOCO 2% labeled dataCOCO 0.5% labeled dataCOCO

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1VCmAP19.46—Unverified
2MUMmAP18.54—Unverified