HyperAIHyperAI

Semi Supervised Image Classification On Cifar

Métriques

Percentage error

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle
Percentage error
Paper TitleRepository
GAN15.59Improved Techniques for Training GANs-
SimMatch3.96SimMatch: Semi-supervised Learning with Similarity Matching-
Self Meta Pseudo Labels4.09Self Meta Pseudo Labels: Meta Pseudo Labels Without The Teacher-
FixMatch+DM4.13±0.11--
LiDAM7.48LiDAM: Semi-Supervised Learning with Localized Domain Adaptation and Iterative Matching-
Meta Pseudo Labels (WRN-28-2)3.89± 0.07Meta Pseudo Labels-
LaplaceNet (CNN-13)4.99±0.08LaplaceNet: A Hybrid Graph-Energy Neural Network for Deep Semi-Supervised Classification-
ReMixMatch5.14ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring-
EnAET4.18EnAET: A Self-Trained framework for Semi-Supervised and Supervised Learning with Ensemble Transformations-
DoubleMatch4.65±0.17DoubleMatch: Improving Semi-Supervised Learning with Self-Supervision-
UDA5.27Unsupervised Data Augmentation for Consistency Training-
VAT11.36Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning-
Triple-GAN-V2 (CNN-13)10.01Triple Generative Adversarial Networks-
GLOT-DR10.6Global-Local Regularization Via Distributional Robustness-
FlexMatch4.19±0.01FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling-
UPS (Shake-Shake)4.86In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning-
SWSA5There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average-
Diff-SySC3.26±0.06Diff-SySC: An Approach Using Diffusion Models for Semi-Supervised Image Classification-
Dual Student (600)8.89Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning-
Dash (RA, ours)4.08±0.06Dash: Semi-Supervised Learning with Dynamic Thresholding-
0 of 47 row(s) selected.
Semi Supervised Image Classification On Cifar | SOTA | HyperAI