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 141–150 of 265 papers

TitleStatusHype
Greedy-layer Pruning: Speeding up Transformer Models for Natural Language ProcessingCode0
Initialization and Regularization of Factorized Neural LayersCode1
Audio Transformers—0
SYNFIX: Automatically Fixing Syntax Errors using Compiler Diagnostics—0
A Large-Scale Study on Unsupervised Spatiotemporal Representation LearningCode0
Representation Learning for Weakly Supervised Relation Extraction—0
Patient Contrastive Learning: a Performant, Expressive, and Practical Approach to ECG ModelingCode1
On Architectures and Training for Raw Waveform Feature Extraction in ASR—0
Maximal Multiverse Learning for Promoting Cross-Task Generalization of Fine-Tuned Language Models—0
Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing DataCode1
Show:102550
← PrevPage 15 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