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 111–120 of 265 papers

TitleStatusHype
ELECTRIcity: An Efficient Transformer for Non-Intrusive Load MonitoringCode1
Large-Scale Pre-training for Person Re-identification with Noisy LabelsCode2
Reinforcement Learning with Action-Free Pre-Training from VideosCode1
Unsupervised Pre-training for Temporal Action Localization TasksCode1
Unsupervised Pre-Training on Patient Population Graphs for Patient-Level PredictionsCode1
COLA: COarse LAbel pre-training for 3D semantic segmentation of sparse LiDAR datasetsCode0
Boundary-aware Information Maximization for Self-supervised Medical Image Segmentation—0
Korean-Specific Dataset for Table Question AnsweringCode1
The CLEAR Benchmark: Continual LEArning on Real-World ImageryCode1
3D Intracranial Aneurysm Classification and Segmentation via Unsupervised Dual-branch Learning—0
Show:102550
← PrevPage 12 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