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 51–60 of 265 papers

TitleStatusHype
Behavior From the Void: Unsupervised Active Pre-TrainingCode1
ES-Net: An Efficient Stereo Matching NetworkCode1
DOBF: A Deobfuscation Pre-Training Objective for Programming LanguagesCode1
CATE: Computation-aware Neural Architecture Encoding with TransformersCode1
Unsupervised Semantic Segmentation by Contrasting Object Mask ProposalsCode1
FedAUX: Leveraging Unlabeled Auxiliary Data in Federated LearningCode1
SEED: Self-supervised Distillation For Visual RepresentationCode1
End-to-End Training of Neural Retrievers for Open-Domain Question AnsweringCode1
OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised LearningCode1
TabTransformer: Tabular Data Modeling Using Contextual EmbeddingsCode1
Show:102550
← PrevPage 6 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