HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

Semi Supervised Image Classification On Svhn

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Model Name
Accuracy
Paper TitleRepository
Triple-GAN-V2 (CNN-13, no aug)96.04Triple Generative Adversarial Networks
UDA97.54Unsupervised Data Augmentation for Consistency Training
DoubleMatch97.90 ± 0.07DoubleMatch: Improving Semi-Supervised Learning with Self-Supervision
ICT (WRN-28-2)96.47Interpolation Consistency Training for Semi-Supervised Learning
ICT96.11Interpolation Consistency Training for Semi-Supervised Learning
SESEMI SSL (ConvNet)94.41Exploring Self-Supervised Regularization for Supervised and Semi-Supervised Learning
MixMatch96.73MixMatch: A Holistic Approach to Semi-Supervised Learning
GAN91.89Improved Techniques for Training GANs
Meta Pseudo Labels (WRN-28-2)98.01 ± 0.07Meta Pseudo Labels
Triple-GAN-V2 (CNN-13)96.55Triple Generative Adversarial Networks
Mean Teacher96.05Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
FixMatch (CTA)97.64±0.19FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
ReMixMatch97.17ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring-
VAT94.58Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
R2-D2 (CNN-13)96.36Repetitive Reprediction Deep Decipher for Semi-Supervised Learning
FCE96.13Flow Contrastive Estimation of Energy-Based Models
EnAET97.58EnAET: A Self-Trained framework for Semi-Supervised and Supervised Learning with Ensemble Transformations
0 of 17 row(s) selected.