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 101–110 of 265 papers

TitleStatusHype
Author2Vec: A Framework for Generating User Embedding—0
Corruption Is Not All Bad: Incorporating Discourse Structure into Pre-training via Corruption for Essay Scoring—0
Is MixIT Really Unsuitable for Correlated Sources? Exploring MixIT for Unsupervised Pre-training in Music Source Separation—0
Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning—0
GiBERT: Introducing Linguistic Knowledge into BERT through a Lightweight Gated Injection Method—0
Cross-Domain Training for Goal-Oriented Conversational Agents—0
Large Language Model Enabled Semantic Communication Systems—0
FairSISA: Ensemble Post-Processing to Improve Fairness of Unlearning in LLMs—0
Generalized 3D Self-supervised Learning Framework via Prompted Foreground-Aware Feature Contrast—0
Co-Morbidity Exploration on Wearables Activity Data Using Unsupervised Pre-training and Multi-Task Learning—0
Show:102550
← PrevPage 11 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