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 201–225 of 265 papers

TitleStatusHype
Author2Vec: A Framework for Generating User Embedding—0
Transfer Learning for Context-Aware Spoken Language Understanding—0
Unsupervised Pre-trained, Texture Aware And Lightweight Model for Deep Learning-Based Iris Recognition Under Limited Annotated Data—0
Synthetic vascular structure generation for unsupervised pre-training in CTA segmentation tasks—0
Unsupervised Pre-training for Natural Language Generation: A Literature Review—0
SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug DiscoveryCode0
MML: Maximal Multiverse Learning for Robust Fine-Tuning of Language ModelsCode0
Combining Unsupervised Pre-training and Annotator Rationales to Improve Low-shot Text Classification—0
Empirical Evaluation of Active Learning Techniques for Neural MT—0
Recognizing UMLS Semantic Types with Deep Learning—0
Extractive NarrativeQA with Heuristic Pre-Training—0
Unsupervised pre-training for sequence to sequence speech recognition—0
Pre-train and Learn: Preserve Global Information for Graph Neural NetworksCode0
Improving Transformer-based Speech Recognition Using Unsupervised Pre-trainingCode1
Extracting UMLS Concepts from Medical Text Using General and Domain-Specific Deep Learning Models—0
SMiRL: Surprise Minimizing RL in Entropic Environments—0
Understanding Semantics from Speech Through Pre-training—0
Bridging the domain gap in cross-lingual document classificationCode0
Effective training of deep convolutional neural networks for hyperspectral image classification through artificial labeling—0
Cross-Domain Training for Goal-Oriented Conversational Agents—0
Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic DataCode0
Tuning Multilingual Transformers for Language-Specific Named Entity RecognitionCode0
Leveraging Pre-trained Checkpoints for Sequence Generation TasksCode1
Exploiting Unsupervised Pre-training and Automated Feature Engineering for Low-resource Hate Speech Detection in Polish—0
Improving Relation Extraction by Pre-trained Language RepresentationsCode0
Show:102550
← PrevPage 9 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