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 211–220 of 265 papers

TitleStatusHype
Unsupervised Pre-training With Seq2Seq Reconstruction Loss for Deep Relation Extraction Models—0
Unsupervised Pre-training with Structured Knowledge for Improving Natural Language Inference—0
VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain—0
Weakly Supervised Construction of ASR Systems with Massive Video Data—0
What is the Best Feature Learning Procedure in Hierarchical Recognition Architectures?—0
What Makes for Good Views for Contrastive Learning?—0
Range-aware Positional Encoding via High-order Pretraining: Theory and Practice—0
Recognizing UMLS Semantic Types with Deep Learning—0
Representation Learning for Weakly Supervised Relation Extraction—0
Pre-train and Learn: Preserve Global Information for Graph Neural NetworksCode0
Show:102550
← PrevPage 22 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