SOTAVerified

Unsupervised Pre-training

Pre-training a neural network using unsupervised (self-supervised) auxiliary tasks on unlabeled data.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 21–30 of 265 papers

TitleStatusHype
Rethinking Semi-supervised Learning with Language ModelsCode1
PTGB: Pre-Train Graph Neural Networks for Brain Network AnalysisCode1
FreePoint: Unsupervised Point Cloud Instance SegmentationCode1
Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful LearnerCode1
Unsupervised Pre-Training For Data-Efficient Text-to-Speech On Low Resource LanguagesCode1
MultiTalent: A Multi-Dataset Approach to Medical Image SegmentationCode1
DocILE Benchmark for Document Information Localization and ExtractionCode1
ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object DetectionCode1
Unsupervised pre-training of graph transformers on patient population graphsCode1
CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World DomainsCode1
Show:102550
← PrevPage 3 of 27Next →
All datasetsMeaslesUCI measles

Benchmark Results

#ModelMetricClaimedVerifiedStatus
115RDLsAccuracy (%)95—Unverified
29RDLsAccuracy (%)94—Unverified
33 RMDLAccuracy (%)93—Unverified
4CNNAccuracy (%)73—Unverified
5RMDLAccuracy (%)0.1—Unverified
#ModelMetricClaimedVerifiedStatus
1RMDL (30 RDLs)Sensitivity (VEB)90.69—Unverified
2Sensitivity89.1—Unverified
3RMDL 3 RDLsSensitivity0.87—Unverified