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 1–50 of 167 papers

Title	Date	Tasks	Status	Hype	Score
FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning	May 15, 2022	FairnessSemi-Supervised Image Classification	CodeCode Available	3	5
USB: A Unified Semi-supervised Learning Benchmark for Classification	Aug 12, 2022	General ClassificationGPU	CodeCode Available	3	5
Masked Siamese Networks for Label-Efficient Learning	Apr 14, 2022	image-classificationImage Classification	CodeCode Available	2	5
Learning Transferable Visual Models From Natural Language Supervision	Feb 26, 2021	Action RecognitionBenchmarking	CodeCode Available	2	5
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments	Jun 17, 2020	Contrastive LearningData Augmentation	CodeCode Available	2	5
FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling	Oct 15, 2021	Semi-Supervised Image Classification	CodeCode Available	2	5
A Simple Framework for Contrastive Learning of Visual Representations	Feb 13, 2020	Contrastive LearningImage Classification	CodeCode Available	2	5
Big Self-Supervised Models are Strong Semi-Supervised Learners	Jun 17, 2020	Self-Supervised Image ClassificationSemi-Supervised Image Classification	CodeCode Available	2	5
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence	Jan 21, 2020	Image ClassificationPseudo Label	CodeCode Available	2	5
SCAN: Learning to Classify Images without Labels	May 25, 2020	ClassificationClustering	CodeCode Available	2	5
Prototypical Contrastive Learning of Unsupervised Representations	May 11, 2020	ClusteringContrastive Learning	CodeCode Available	1	5
NP-Match: When Neural Processes meet Semi-Supervised Learning	Jul 3, 2022	image-classificationImage Classification	CodeCode Available	1	5
batchboost: regularization for stabilizing training with resistance to underfitting & overfitting	Jan 21, 2020	Image ClassificationSemi-Supervised Image Classification	CodeCode Available	1	5
OpenMatch: Open-Set Semi-supervised Learning with Open-set Consistency Regularization	Dec 1, 2021	Novelty DetectionOutlier Detection	CodeCode Available	1	5
All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training	Apr 12, 2021	AllSemi-Supervised Image Classification	CodeCode Available	1	5
NP-SemiSeg: When Neural Processes meet Semi-Supervised Semantic Segmentation	Aug 5, 2023	image-classificationImage Classification	CodeCode Available	1	5
ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring	Nov 21, 2019	Image ClassificationSemi-Supervised Image Classification	CodeCode Available	1	5
mixup: Beyond Empirical Risk Minimization	Oct 25, 2017	Domain GeneralizationImage Classification	CodeCode Available	1	5
Meta Pseudo Labels	Mar 23, 2020	Image ClassificationMeta-Learning	CodeCode Available	1	5
In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning	Jan 15, 2021	Multi-Label ClassificationMUlTI-LABEL-ClASSIFICATION	CodeCode Available	1	5
A Self-ensembling Framework for Semi-supervised Knee Cartilage Defects Assessment with Dual-Consistency	May 19, 2020	ClassificationGeneral Classification	CodeCode Available	1	5
Class-Aware Contrastive Semi-Supervised Learning	Mar 4, 2022	Image ClassificationPseudo Label	CodeCode Available	1	5
MixMatch: A Holistic Approach to Semi-Supervised Learning	May 6, 2019	Image ClassificationSemi-Supervised Image Classification	CodeCode Available	1	5
LaplaceNet: A Hybrid Graph-Energy Neural Network for Deep Semi-Supervised Classification	Jun 8, 2021	Semi-Supervised Image Classification	CodeCode Available	1	5
Barlow Twins: Self-Supervised Learning via Redundancy Reduction	Mar 4, 2021	General ClassificationImage Classification	CodeCode Available	1	5
KeepAugment: A Simple Information-Preserving Data Augmentation Approach	Nov 23, 2020	Data AugmentationGeneral Classification	CodeCode Available	1	5
MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularization	Mar 27, 2022	Semi-Supervised Image Classification	CodeCode Available	1	5
Large Scale Adversarial Representation Learning	Jul 4, 2019	Contrastive LearningImage Generation	CodeCode Available	1	5
Learning Customized Visual Models with Retrieval-Augmented Knowledge	Jan 17, 2023	Contrastive LearningRetrieval	CodeCode Available	1	5
OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning	Dec 21, 2020	object-detectionObject Detection	CodeCode Available	1	5
A New Semi-supervised Learning Benchmark for Classifying View and Diagnosing Aortic Stenosis from Echocardiograms	Jul 30, 2021	image-classificationImage Classification	CodeCode Available	1	5
Boosting Contrastive Self-Supervised Learning with False Negative Cancellation	Nov 23, 2020	Contrastive LearningRepresentation Learning	CodeCode Available	1	5
Improved Regularization of Convolutional Neural Networks with Cutout	Aug 15, 2017	Data AugmentationDomain Generalization	CodeCode Available	1	5
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results	Mar 6, 2017	Semi-Supervised Image ClassificationSemi-Supervised RGBD Semantic Segmentation	CodeCode Available	1	5
iBOT: Image BERT Pre-Training with Online Tokenizer	Nov 15, 2021	image-classificationImage Classification	CodeCode Available	1	5
DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning	Jun 10, 2021	imbalanced classificationPseudo Label	CodeCode Available	1	5
Improved Techniques for Training GANs	Jun 10, 2016	Conditional Image GenerationImage Generation	CodeCode Available	1	5
Implicit Rank-Minimizing Autoencoder	Oct 1, 2020	DecoderImage Generation	CodeCode Available	1	5
Bootstrap your own latent: A new approach to self-supervised Learning	Jun 13, 2020	Image ClassificationLinear evaluation	CodeCode Available	1	5
EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANs	Dec 26, 2020	ClassificationData Augmentation	CodeCode Available	1	5
Building One-Shot Semi-supervised (BOSS) Learning up to Fully Supervised Performance	Jun 16, 2020	Semi-Supervised Image Classification	CodeCode Available	1	5
Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning	Jan 21, 2021	Self-Supervised LearningSemi-Supervised Image Classification	CodeCode Available	1	5
FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning	Jul 16, 2020	ClusteringData Augmentation	CodeCode Available	1	5
Debiased Self-Training for Semi-Supervised Learning	Feb 15, 2022	Object RecognitionScene Classification	CodeCode Available	1	5
Debiased Learning from Naturally Imbalanced Pseudo-Labels	Jan 5, 2022	counterfactualCounterfactual Reasoning	CodeCode Available	1	5
Flow Contrastive Estimation of Energy-Based Models	Dec 2, 2019	Image GenerationSemi-Supervised Image Classification	CodeCode Available	1	5
Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation	Mar 29, 2021	Domain AdaptationScene Segmentation	CodeCode Available	1	5
InfoMatch: Entropy Neural Estimation for Semi-Supervised Image Classification	Apr 17, 2024	Contrastive Learningimage-classification	CodeCode Available	1	5
CoMatch: Semi-supervised Learning with Contrastive Graph Regularization	Nov 23, 2020	Contrastive LearningRepresentation Learning	CodeCode Available	1	5
Meta Co-Training: Two Views are Better than One	Nov 29, 2023	Fine-Grained Image Classificationimage-classification	CodeCode Available	1	5

Show:10 25 50

← PrevPage 1 of 4Next →

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	SimCLR (ResNet-50 4×)	Top 5 Accuracy	92.6	—	Unverified
2	Rotation + VAT + Ent. Min.	Top 5 Accuracy	91.23	—	Unverified
3	SimCLR (ResNet-50 2×)	Top 5 Accuracy	91.2	—	Unverified
4	Mean Teacher (ResNeXt-152)	Top 5 Accuracy	90.89	—	Unverified
5	OBoW (ResNet-50)	Top 5 Accuracy	90.7	—	Unverified
6	R2-D2 (ResNet-18)	Top 5 Accuracy	90.48	—	Unverified
7	FixMatch	Top 5 Accuracy	89.13	—	Unverified
8	UDA	Top 5 Accuracy	88.52	—	Unverified
9	SimCLR (ResNet-50)	Top 5 Accuracy	87.8	—	Unverified
10	DHO (ViT-Large)	Top 1 Accuracy	85.9	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DHO (ViT-Large)	Top 1 Accuracy	84.6	—	Unverified
2	OBoW (ResNet-50)	Top 5 Accuracy	82.9	—	Unverified
3	DHO (ViT-Base)	Top 1 Accuracy	81.6	—	Unverified
4	REACT (ViT-Large)	Top 1 Accuracy	81.6	—	Unverified
5	Meta Co-Training	Top 1 Accuracy	80.7	—	Unverified
6	Semi-SST (ViT-Huge)	Top 1 Accuracy	80.7	—	Unverified
7	Super-SST (ViT-Huge)	Top 1 Accuracy	80.3	—	Unverified
8	Semi-ViT (ViT-Huge)	Top 1 Accuracy	80	—	Unverified
9	Semi-ViT (ViT-Large)	Top 1 Accuracy	77.3	—	Unverified
10	Super-SST (ViT-Small distilled)	Top 1 Accuracy	76.9	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Γ-model	Percentage error	20.4	—	Unverified
2	GAN	Percentage error	15.59	—	Unverified
3	Bad GAN	Percentage error	14.41	—	Unverified
4	Triple-GAN-V2 (CNN-13, no aug)	Percentage error	12.41	—	Unverified
5	Pi Model	Percentage error	12.16	—	Unverified
6	SESEMI SSL (ConvNet)	Percentage error	11.65	—	Unverified
7	VAT	Percentage error	11.36	—	Unverified
8	GLOT-DR	Percentage error	10.6	—	Unverified
9	VAT+EntMin	Percentage error	10.55	—	Unverified
10	Triple-GAN-V2 (CNN-13)	Percentage error	10.01	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Ⅱ-Model	Percentage error	39.19	—	Unverified
2	SESEMI SSL (ConvNet)	Percentage error	38.7	—	Unverified
3	Temporal ensembling	Percentage error	38.65	—	Unverified
4	R2-D2 (CNN-13)	Percentage error	32.87	—	Unverified
5	Dual Student (480)	Percentage error	32.77	—	Unverified
6	UPS (CNN-13)	Percentage error	32	—	Unverified
7	SHOT-VAE	Percentage error	25.3	—	Unverified
8	LiDAM	Percentage error	23.22	—	Unverified
9	EnAET (WRN-28-2-Large)	Percentage error	22.92	—	Unverified
10	FixMatch (RA, WRN-28-8)	Percentage error	22.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Ⅱ-Model	Percentage error	53.12	—	Unverified
2	MixUp	Percentage error	47.43	—	Unverified
3	MeanTeacher	Percentage error	47.32	—	Unverified
4	VAT	Percentage error	36.03	—	Unverified
5	LiDAM	Percentage error	19.17	—	Unverified
6	MixMatch	Percentage error	11.08	—	Unverified
7	RealMix	Percentage error	9.79	—	Unverified
8	EnAET	Percentage error	7.6	—	Unverified
9	ReMixMatch	Percentage error	6.27	—	Unverified
10	FixMatch+CR	Percentage error	5.04	—	Unverified