SOTAVerified

Unsupervised Pre-training

Pre-training a neural network using unsupervised (self-supervised) auxiliary tasks on unlabeled data.

Papers

Showing 2650 of 265 papers

TitleStatusHype
MultiTalent: A Multi-Dataset Approach to Medical Image SegmentationCode1
DocILE Benchmark for Document Information Localization and ExtractionCode1
ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object DetectionCode1
Unsupervised pre-training of graph transformers on patient population graphsCode1
CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World DomainsCode1
Self-Supervised Visual Representation Learning with Semantic GroupingCode1
Semi-supervised 3D shape segmentation with multilevel consistency and part substitutionCode1
ELECTRIcity: An Efficient Transformer for Non-Intrusive Load MonitoringCode1
Unsupervised Pre-training for Temporal Action Localization TasksCode1
Reinforcement Learning with Action-Free Pre-Training from VideosCode1
Unsupervised Pre-Training on Patient Population Graphs for Patient-Level PredictionsCode1
Korean-Specific Dataset for Table Question AnsweringCode1
The CLEAR Benchmark: Continual LEArning on Real-World ImageryCode1
AI-Bind: Improving Binding Predictions for Novel Protein Targets and LigandsCode1
SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual RepresentationsCode1
Bag of Tricks and A Strong baseline for Image Copy DetectionCode1
D^2LV: A Data-Driven and Local-Verification Approach for Image Copy DetectionCode1
Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech RecognitionCode1
RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object DetectionCode1
PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-trainingCode1
Exploring the Limits of Out-of-Distribution DetectionCode1
Initialization and Regularization of Factorized Neural LayersCode1
Patient Contrastive Learning: a Performant, Expressive, and Practical Approach to ECG ModelingCode1
Pre-training strategies and datasets for facial representation learningCode1
Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing DataCode1
Show:102550
← PrevPage 2 of 11Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
115RDLsAccuracy (%)95Unverified
29RDLsAccuracy (%)94Unverified
33 RMDLAccuracy (%)93Unverified
4CNNAccuracy (%)73Unverified
5RMDLAccuracy (%)0.1Unverified
#ModelMetricClaimedVerifiedStatus
1RMDL (30 RDLs)Sensitivity (VEB)90.69Unverified
2Sensitivity89.1Unverified
3RMDL 3 RDLsSensitivity0.87Unverified