Semi Supervised Image Classification On Cifar 2

Metrics

Percentage error

Results

Performance results of various models on this benchmark

Model Name	Percentage error	Paper Title	Repository
SMPL (WRN-28-8)	21.68	Self Meta Pseudo Labels: Meta Pseudo Labels Without The Teacher	-
Dash (RA, WRN-28-8)	21.97±0.14	Dash: Semi-Supervised Learning with Dynamic Thresholding	-
CCSSL(FixMatch)	19.32	Class-Aware Contrastive Semi-Supervised Learning
FlexMatch	21.90±0.15	FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling
FreeMatch	21.68	FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning
Ⅱ-Model	39.19	Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning	-
SimPLE (WRN-28-8)	21.89	SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classification
SHOT-VAE	25.3	SHOT-VAE: Semi-supervised Deep Generative Models With Label-aware ELBO Approximations
R2-D2 (CNN-13)	32.87	Repetitive Reprediction Deep Decipher for Semi-Supervised Learning
LaplaceNet (WRN-28-8)	22.11± 0.23	LaplaceNet: A Hybrid Graph-Energy Neural Network for Deep Semi-Supervised Classification
SimMatch	20.58	SimMatch: Semi-supervised Learning with Similarity Matching
Dual Student (480)	32.77	Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning
DP-SSL	22.24±0.31	DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samples	-
SemCo (μ=7)	24.45±0.12	All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training
FixMatch (CTA, WRN-28-8)	23.18±0.11	FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
Temporal ensembling	38.65	Temporal Ensembling for Semi-Supervised Learning
NP-Match	21.22	NP-Match: When Neural Processes meet Semi-Supervised Learning
CowMix (WRN-28-96x2d)	23.07±0.30	Milking CowMask for Semi-Supervised Image Classification
EnAET (WRN-28-2)	26.93±0.21	EnAET: A Self-Trained framework for Semi-Supervised and Supervised Learning with Ensemble Transformations
FixMatch+CR	21.03	Contrastive Regularization for Semi-Supervised Learning	-

0 of 27 row(s) selected.