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 61–70 of 265 papers

TitleStatusHype
Unsupervised Pre-training for Person Re-identificationCode1
UP-DETR: Unsupervised Pre-training for Object Detection with TransformersCode1
MAGNeto: An Efficient Deep Learning Method for the Extractive Tags Summarization ProblemCode1
Image Representations Learned With Unsupervised Pre-Training Contain Human-like BiasesCode1
Unsupervised Vision-and-Language Pre-training Without Parallel Images and CaptionsCode1
A Transformer-based Framework for Multivariate Time Series Representation LearningCode1
Self-training Improves Pre-training for Natural Language UnderstandingCode1
Spatiotemporal Contrastive Video Representation LearningCode1
SeCo: Exploring Sequence Supervision for Unsupervised Representation LearningCode1
PointContrast: Unsupervised Pre-training for 3D Point Cloud UnderstandingCode1
Show:102550
← PrevPage 7 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