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 71–80 of 265 papers

TitleStatusHype
Leveraging Pre-trained Checkpoints for Sequence Generation TasksCode1
Drop your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage RetrievalCode1
Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech RecognitionCode1
METRA: Scalable Unsupervised RL with Metric-Aware AbstractionCode1
Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing DataCode1
ELECTRIcity: An Efficient Transformer for Non-Intrusive Load MonitoringCode1
CATE: Computation-aware Neural Architecture Encoding with TransformersCode1
OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised LearningCode1
Deep Features for CBIR with Scarce Data using Hebbian Learning—0
BID: Boundary-Interior Decoding for Unsupervised Temporal Action Localization Pre-Trainin—0
Show:102550
← PrevPage 8 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