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 11–20 of 265 papers

TitleStatusHype
How much do LLMs learn from negative examples?Code0
Pretraining Generative Flow Networks with Inexpensive Rewards for Molecular Graph Generation—0
Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models—0
Targeted Forgetting of Image Subgroups in CLIP Models—0
Incomplete Multi-View Multi-label Learning via Disentangled Representation and Label Semantic Embedding—0
HindiLLM: Large Language Model for Hindi—0
FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation LearningCode2
Transferring self-supervised pre-trained models for SHM data anomaly detection with scarce labeled data—0
CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learning—0
Point Cloud Unsupervised Pre-training via 3D Gaussian Splatting—0
Show:102550
← PrevPage 2 of 27Next →
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