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 251–260 of 265 papers

TitleStatusHype
Targeted Forgetting of Image Subgroups in CLIP Models—0
Temporal Autoencoding Improves Generative Models of Time Series—0
Temporal Interpolation as an Unsupervised Pretraining Task for Optical Flow Estimation—0
The Efficiency of Pre-training with Objective Masking in Pseudo Labeling for Semi-Supervised Text Classification—0
Towards General Text Embeddings with Multi-stage Contrastive Learning—0
TraIL-Det: Transformation-Invariant Local Feature Networks for 3D LiDAR Object Detection with Unsupervised Pre-Training—0
Transfer Learning for Context-Aware Spoken Language Understanding—0
Transferring self-supervised pre-trained models for SHM data anomaly detection with scarce labeled data—0
Triplet Contrastive Learning for Brain Tumor Classification—0
UHH-LT at SemEval-2019 Task 6: Supervised vs. Unsupervised Transfer Learning for Offensive Language Detection—0
Show:102550
← PrevPage 26 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