SOTAVerified

Unsupervised Pre-training

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

Papers

Showing 226250 of 265 papers

TitleStatusHype
On the Generalization Ability of Unsupervised Pretraining0
Unsupervised Deep Representation Learning and Few-Shot Classification of PolSAR Images0
Point Cloud Unsupervised Pre-training via 3D Gaussian Splatting0
Post-training for Deep Learning0
Pre-Training and Fine-Tuning Generative Flow Networks0
Pretraining Generative Flow Networks with Inexpensive Rewards for Molecular Graph Generation0
Pre-training Text Representations as Meta Learning0
Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models0
Range-aware Positional Encoding via High-order Pretraining: Theory and Practice0
Recognizing UMLS Semantic Types with Deep Learning0
Representation Learning for Weakly Supervised Relation Extraction0
Research on CPI Prediction Based on Natural Language Processing0
Residual Contrastive Learning for Image Reconstruction: Learning Transferable Representations from Noisy Images0
Risk Assessment Framework for Code LLMs via Leveraging Internal States0
R-LAtte: Attention Module for Visual Control via Reinforcement Learning0
Self-FuseNet: Data Free Unsupervised Remote Sensing Image Super-Resolution0
Self-Supervised Relative Depth Learning for Urban Scene Understanding0
Semi-supervised Facial Action Unit Intensity Estimation with Contrastive Learning0
Semi-Supervised End-To-End Contrastive Learning For Time Series Classification0
Semi-Supervised Semantic Segmentation of Cell Nuclei via Diffusion-based Large-Scale Pre-Training and Collaborative Learning0
SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training0
SMiRL: Surprise Minimizing RL in Entropic Environments0
Spiral Contrastive Learning: An Efficient 3D Representation Learning Method for Unannotated CT Lesions0
SYNFIX: Automatically Fixing Syntax Errors using Compiler Diagnostics0
Synthetic vascular structure generation for unsupervised pre-training in CTA segmentation tasks0
Show:102550
← PrevPage 10 of 11Next →

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