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 31–40 of 265 papers

TitleStatusHype
CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World DomainsCode1
FreePoint: Unsupervised Point Cloud Instance SegmentationCode1
HIQL: Offline Goal-Conditioned RL with Latent States as ActionsCode1
Image Representations Learned With Unsupervised Pre-Training Contain Human-like BiasesCode1
ConStyle v2: A Strong Prompter for All-in-One Image RestorationCode1
Drop your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage RetrievalCode1
FedAUX: Leveraging Unlabeled Auxiliary Data in Federated LearningCode1
CATE: Computation-aware Neural Architecture Encoding with TransformersCode1
BMRetriever: Tuning Large Language Models as Better Biomedical Text RetrieversCode1
D^2LV: A Data-Driven and Local-Verification Approach for Image Copy DetectionCode1
Show:102550
← PrevPage 4 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