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 61–70 of 265 papers

TitleStatusHype
Multilingual Constituency Parsing with Self-Attention and Pre-TrainingCode1
PointContrast: Unsupervised Pre-training for 3D Point Cloud UnderstandingCode1
Rolling-Unrolling LSTMs for Action Anticipation from First-Person VideoCode1
Drop your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage RetrievalCode1
BMRetriever: Tuning Large Language Models as Better Biomedical Text RetrieversCode1
ELECTRIcity: An Efficient Transformer for Non-Intrusive Load MonitoringCode1
DOBF: A Deobfuscation Pre-Training Objective for Programming LanguagesCode1
DocILE Benchmark for Document Information Localization and ExtractionCode1
Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful LearnerCode1
Unsupervised Pre-Training For Data-Efficient Text-to-Speech On Low Resource LanguagesCode1
Show:102550
← PrevPage 7 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