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 231–240 of 265 papers

TitleStatusHype
Unsupervised pre-training helps to conserve views from input distribution—0
Unsupervised Pre-Training of Image Features on Non-Curated DataCode0
BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task LearningCode0
Tuning Multilingual Transformers for Named Entity Recognition on Slavic LanguagesCode0
Unsupervised Transfer Learning for Spoken Language Understanding in Intelligent AgentsCode0
Leveraging Random Label Memorization for Unsupervised Pre-Training—0
Advancing PICO Element Detection in Biomedical Text via Deep Neural NetworksCode0
Temporal Interpolation as an Unsupervised Pretraining Task for Optical Flow Estimation—0
Deep Belief Networks Based Feature Generation and Regression for Predicting Wind Power—0
Deep Discriminative Model for Video Classification—0
Show:102550
← PrevPage 24 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