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 91–100 of 265 papers

TitleStatusHype
DocILE Benchmark for Document Information Localization and ExtractionCode1
Boosting Low-Data Instance Segmentation by Unsupervised Pre-training with Saliency Prompt—0
Self-FuseNet: Data Free Unsupervised Remote Sensing Image Super-Resolution—0
Unsupervised Pre-Training for Vietnamese Automatic Speech Recognition in the HYKIST Project—0
Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document UnderstandingCode0
ACROBAT -- a multi-stain breast cancer histological whole-slide-image data set from routine diagnostics for computational pathology—0
EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model—0
Spiral Contrastive Learning: An Efficient 3D Representation Learning Method for Unannotated CT Lesions—0
Evaluate Confidence Instead of Perplexity for Zero-shot Commonsense Reasoning—0
ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object DetectionCode1
Show:102550
← PrevPage 10 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