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 101–125 of 265 papers

TitleStatusHype
Generalized 3D Self-supervised Learning Framework via Prompted Foreground-Aware Feature ContrastCode0
RMDL: Random Multimodel Deep Learning for ClassificationCode0
A Large-Scale Study on Unsupervised Spatiotemporal Representation LearningCode0
GiBERT: Enhancing BERT with Linguistic Information using a Lightweight Gated Injection MethodCode0
COLA: COarse LAbel pre-training for 3D semantic segmentation of sparse LiDAR datasetsCode0
Self-Supervised Modality-Agnostic Pre-Training of Swin TransformersCode0
CochCeps-Augment: A Novel Self-Supervised Contrastive Learning Using Cochlear Cepstrum-based Masking for Speech Emotion RecognitionCode0
Post Training in Deep Learning with Last KernelCode0
Pre-train and Learn: Preserve Global Information for Graph Neural NetworksCode0
How much do LLMs learn from negative examples?Code0
PUNR: Pre-training with User Behavior Modeling for News RecommendationCode0
Self-Supervised Pre-Training Boosts Semantic Scene Segmentation on LiDAR DataCode0
Learning of feature points without additional supervision improves reinforcement learning from imagesCode0
Calibrating Language Models with Adaptive Temperature ScalingCode0
Bridging the domain gap in cross-lingual document classificationCode0
Advancing PICO Element Detection in Biomedical Text via Deep Neural NetworksCode0
Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic DataCode0
m2caiSeg: Semantic Segmentation of Laparoscopic Images using Convolutional Neural NetworksCode0
MML: Maximal Multiverse Learning for Robust Fine-Tuning of Language ModelsCode0
Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human FeedbackCode0
Learning Deep Representations Using Convolutional Auto-encoders with Symmetric Skip ConnectionsCode0
Unsupervised Pre-Training of Image Features on Non-Curated DataCode0
From Recognition to Prediction: Leveraging Sequence Reasoning for Action AnticipationCode0
LATTE: Label-efficient Incident Phenotyping from Longitudinal Electronic Health RecordsCode0
What Makes for Good Views for Contrastive Learning?Code0
Show:102550
← PrevPage 5 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