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 26–50 of 265 papers

TitleStatusHype
Bag of Tricks and A Strong baseline for Image Copy DetectionCode1
Behavior From the Void: Unsupervised Active Pre-TrainingCode1
PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-trainingCode1
PersonViT: Large-scale Self-supervised Vision Transformer for Person Re-IdentificationCode1
PointContrast: Unsupervised Pre-training for 3D Point Cloud UnderstandingCode1
Image Representations Learned With Unsupervised Pre-Training Contain Human-like BiasesCode1
MAGNeto: An Efficient Deep Learning Method for the Extractive Tags Summarization ProblemCode1
CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World DomainsCode1
ES-Net: An Efficient Stereo Matching NetworkCode1
End-to-End Training of Neural Retrievers for Open-Domain Question AnsweringCode1
Exact solutions to the nonlinear dynamics of learning in deep linear neural networksCode1
Exploring the Limits of Out-of-Distribution DetectionCode1
CATE: Computation-aware Neural Architecture Encoding with TransformersCode1
Drop your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage RetrievalCode1
Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful LearnerCode1
A Transformer-based Framework for Multivariate Time Series Representation LearningCode1
BMRetriever: Tuning Large Language Models as Better Biomedical Text RetrieversCode1
A Further Study of Unsupervised Pre-training for Transformer Based Speech RecognitionCode1
Improving Transformer-based Speech Recognition Using Unsupervised Pre-trainingCode1
DOBF: A Deobfuscation Pre-Training Objective for Programming LanguagesCode1
DocILE Benchmark for Document Information Localization and ExtractionCode1
ConStyle v2: A Strong Prompter for All-in-One Image RestorationCode1
AI-Bind: Improving Binding Predictions for Novel Protein Targets and LigandsCode1
ELECTRIcity: An Efficient Transformer for Non-Intrusive Load MonitoringCode1
FedAUX: Leveraging Unlabeled Auxiliary Data in Federated LearningCode1
Show:102550
← PrevPage 2 of 11Next →
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