Semi-Supervised Image Classification

Semi-supervised image classification leverages unlabelled data as well as labelled data to increase classification performance.

You may want to read some blog posts to get an overview before reading the papers and checking the leaderboards:

An overview of proxy-label approaches for semi-supervised learning - Sebastian Ruder
Semi-Supervised Learning in Computer Vision - Amit Chaudhary

( Image credit: Self-Supervised Semi-Supervised Learning )

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1–10 of 167 papers

Title	Date	Tasks	Status	Hype
ViTSGMM: A Robust Semi-Supervised Image Recognition Network Using Sparse Labels	Jun 4, 2025	Semi-Supervised Image Classification	CodeCode Available	0
Applications and Effect Evaluation of Generative Adversarial Networks in Semi-Supervised Learning	May 26, 2025	Classificationimage-classification	—Unverified	0
Simple Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimization	May 12, 2025	Few-Shot Image ClassificationKnowledge Distillation	CodeCode Available	0
Weakly Semi-supervised Whole Slide Image Classification by Two-level Cross Consistency Supervision	Apr 16, 2025	Classificationimage-classification	—Unverified	0
Diff-SySC: An Approach Using Diffusion Models for Semi-Supervised Image Classification	Feb 25, 2025	image-classificationImage Classification	—Unverified	0
SynCo: Synthetic Hard Negatives in Contrastive Learning for Better Unsupervised Visual Representations	Oct 3, 2024	Contrastive LearningImage Classification	CodeCode Available	0
Self Adaptive Threshold Pseudo-labeling and Unreliable Sample Contrastive Loss for Semi-supervised Image Classification	Jul 4, 2024	image-classificationImage Classification	—Unverified	0
A Method of Moments Embedding Constraint and its Application to Semi-Supervised Learning	Apr 27, 2024	image-classificationImage Classification	CodeCode Available	0
InfoMatch: Entropy Neural Estimation for Semi-Supervised Image Classification	Apr 17, 2024	Contrastive Learningimage-classification	CodeCode Available	1
Pseudo-label Learning with Calibrated Confidence Using an Energy-based Model	Apr 15, 2024	image-classificationImage Classification	—Unverified	0

Show:10 25 50

← PrevPage 1 of 17Next →

All datasets ImageNet - 10% labeled data ImageNet - 1% labeled data CIFAR-10, 4000 Labels cifar-100, 10000 Labels CIFAR-10, 250 Labels SVHN, 1000 labels SVHN, 250 Labels CIFAR-10, 40 Labels CIFAR-100, 400 Labels CIFAR-10, 1000 Labels CIFAR-100, 2500 Labels STL-10, 1000 Labels

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	EnAET	Accuracy	97.58	—	Unverified
2	UDA	Accuracy	97.54	—	Unverified
3	ReMixMatch	Accuracy	97.17	—	Unverified
4	MixMatch	Accuracy	96.73	—	Unverified
5	Triple-GAN-V2 (CNN-13)	Accuracy	96.55	—	Unverified
6	ICT (WRN-28-2)	Accuracy	96.47	—	Unverified
7	R2-D2 (CNN-13)	Accuracy	96.36	—	Unverified
8	FCE	Accuracy	96.13	—	Unverified
9	ICT	Accuracy	96.11	—	Unverified
10	Mean Teacher	Accuracy	96.05	—	Unverified