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
Initialization and Regularization of Factorized Neural LayersCode1
Image Representations Learned With Unsupervised Pre-Training Contain Human-like BiasesCode1
ELECTRIcity: An Efficient Transformer for Non-Intrusive Load MonitoringCode1
Bag of Tricks and A Strong baseline for Image Copy DetectionCode1
Multilingual Constituency Parsing with Self-Attention and Pre-TrainingCode1
D^2LV: A Data-Driven and Local-Verification Approach for Image Copy DetectionCode1
RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object DetectionCode1
Reinforcement Learning with Action-Free Pre-Training from VideosCode1
Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech RecognitionCode1
Self-Supervised Visual Representation Learning with Semantic GroupingCode1
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