SOTAVerified

Unsupervised Pre-training

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

Papers

Showing 51100 of 265 papers

TitleStatusHype
Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing DataCode1
TabTransformer: Tabular Data Modeling Using Contextual EmbeddingsCode1
HIQL: Offline Goal-Conditioned RL with Latent States as ActionsCode1
Bag of Tricks and A Strong baseline for Image Copy DetectionCode1
Behavior From the Void: Unsupervised Active Pre-TrainingCode1
D^2LV: A Data-Driven and Local-Verification Approach for Image Copy DetectionCode1
A Further Study of Unsupervised Pre-training for Transformer Based Speech RecognitionCode1
Exact solutions to the nonlinear dynamics of learning in deep linear neural networksCode1
Self-Supervised Visual Representation Learning with Semantic GroupingCode1
Semi-supervised 3D shape segmentation with multilevel consistency and part substitutionCode1
Self-training Improves Pre-training for Natural Language UnderstandingCode1
TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction TaskCode1
PTGB: Pre-Train Graph Neural Networks for Brain Network AnalysisCode1
BMRetriever: Tuning Large Language Models as Better Biomedical Text RetrieversCode1
SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation ModelCode1
FreePoint: Unsupervised Point Cloud Instance SegmentationCode1
DOBF: A Deobfuscation Pre-Training Objective for Programming LanguagesCode1
DocILE Benchmark for Document Information Localization and ExtractionCode1
Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful LearnerCode1
Image Representations Learned With Unsupervised Pre-Training Contain Human-like BiasesCode1
Spatiotemporal Contrastive Video Representation LearningCode1
Drop your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage RetrievalCode1
The CLEAR Benchmark: Continual LEArning on Real-World ImageryCode1
Improving Transformer-based Speech Recognition Using Unsupervised Pre-trainingCode1
Unsupervised Pre-Training on Patient Population Graphs for Patient-Level PredictionsCode1
ELECTRIcity: An Efficient Transformer for Non-Intrusive Load MonitoringCode1
CATE: Computation-aware Neural Architecture Encoding with TransformersCode1
Korean-Specific Dataset for Table Question AnsweringCode1
Self-training and Pre-training are Complementary for Speech RecognitionCode0
Self-Supervised Pre-Training Boosts Semantic Scene Segmentation on LiDAR DataCode0
Accelerating Training of Transformer-Based Language Models with Progressive Layer DroppingCode0
Decoupling Exploration and Exploitation for Unsupervised Pre-training with Successor FeaturesCode0
Data-dependent Initializations of Convolutional Neural NetworksCode0
BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task LearningCode0
Curriculum-Based Self-Training Makes Better Few-Shot Learners for Data-to-Text GenerationCode0
An Analysis of Unsupervised Pre-training in Light of Recent AdvancesCode0
A Large-Scale Study on Unsupervised Spatiotemporal Representation LearningCode0
RMDL: Random Multimodel Deep Learning for ClassificationCode0
Contextual embedding and model weighting by fusing domain knowledge on Biomedical Question AnsweringCode0
PUNR: Pre-training with User Behavior Modeling for News RecommendationCode0
Self-Supervised Modality-Agnostic Pre-Training of Swin TransformersCode0
SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug DiscoveryCode0
Post Training in Deep Learning with Last KernelCode0
Pre-train and Learn: Preserve Global Information for Graph Neural NetworksCode0
COLA: COarse LAbel pre-training for 3D semantic segmentation of sparse LiDAR datasetsCode0
Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic DataCode0
CochCeps-Augment: A Novel Self-Supervised Contrastive Learning Using Cochlear Cepstrum-based Masking for Speech Emotion RecognitionCode0
MML: Maximal Multiverse Learning for Robust Fine-Tuning of Language ModelsCode0
Unsupervised Pre-Training of Image Features on Non-Curated DataCode0
m2caiSeg: Semantic Segmentation of Laparoscopic Images using Convolutional Neural NetworksCode0
Show:102550
← PrevPage 2 of 6Next →

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