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
A Further Study of Unsupervised Pre-training for Transformer Based Speech RecognitionCode1
Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful LearnerCode1
AI-Bind: Improving Binding Predictions for Novel Protein Targets and LigandsCode1
End-to-End Training of Neural Retrievers for Open-Domain Question AnsweringCode1
Exact solutions to the nonlinear dynamics of learning in deep linear neural networksCode1
Bag of Tricks and A Strong baseline for Image Copy DetectionCode1
DocILE Benchmark for Document Information Localization and ExtractionCode1
BMRetriever: Tuning Large Language Models as Better Biomedical Text RetrieversCode1
D^2LV: A Data-Driven and Local-Verification Approach for Image Copy DetectionCode1
CATE: Computation-aware Neural Architecture Encoding with TransformersCode1
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