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 251–265 of 265 papers

TitleStatusHype
Contextual embedding and model weighting by fusing domain knowledge on Biomedical Question AnsweringCode0
SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug DiscoveryCode0
Calibrating Language Models with Adaptive Temperature ScalingCode0
Functional Regularization for Representation Learning: A Unified Theoretical PerspectiveCode0
Learning of feature points without additional supervision improves reinforcement learning from imagesCode0
Unleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-IdentificationCode0
SynCo: Synthetic Hard Negatives in Contrastive Learning for Better Unsupervised Visual RepresentationsCode0
A Large-Scale Study on Unsupervised Spatiotemporal Representation LearningCode0
ZS-VCOS: Zero-Shot Outperforms Supervised Video Camouflaged Object SegmentationCode0
Decoupling Exploration and Exploitation for Unsupervised Pre-training with Successor FeaturesCode0
Data-dependent Initializations of Convolutional Neural NetworksCode0
Take Package as Language: Anomaly Detection Using TransformerCode0
Advancing PICO Element Detection in Biomedical Text via Deep Neural NetworksCode0
Bridging the domain gap in cross-lingual document classificationCode0
BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task LearningCode0
Show:102550
← PrevPage 11 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