Semi Supervised Image Classification On Cifar

评估指标

Percentage error

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
Γ-model	20.4	Semi-Supervised Learning with Ladder Networks
GAN	15.59	Improved Techniques for Training GANs
Bad GAN	14.41	Good Semi-supervised Learning that Requires a Bad GAN
Triple-GAN-V2 (CNN-13, no aug)	12.41	Triple Generative Adversarial Networks
Pi Model	12.16	Temporal Ensembling for Semi-Supervised Learning
SESEMI SSL (ConvNet)	11.65	Exploring Self-Supervised Regularization for Supervised and Semi-Supervised Learning
VAT	11.36	Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
GLOT-DR	10.6	Global-Local Regularization Via Distributional Robustness
VAT+EntMin	10.55	Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
Triple-GAN-V2 (CNN-13)	10.01	Triple Generative Adversarial Networks
Dual Student (600)	8.89	Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning
ADA-Net (ConvNet)	8.72	Semi-Supervised Learning by Augmented Distribution Alignment
ICT (WRN-28-2)	7.66	Interpolation Consistency Training for Semi-Supervised Learning
LiDAM	7.48	LiDAM: Semi-Supervised Learning with Localized Domain Adaptation and Iterative Matching	-
ICT (CNN-13)	7.29	Interpolation Consistency Training for Semi-Supervised Learning
Triple-GAN-V2 (ResNet-26)	6.54	Triple Generative Adversarial Networks
UPS (CNN-13)	6.39±0.02	In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning
RealMix	6.38	RealMix: Towards Realistic Semi-Supervised Deep Learning Algorithms
Mean Teacher	6.28	Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
MixMatch	6.24	MixMatch: A Holistic Approach to Semi-Supervised Learning

0 of 47 row(s) selected.