SOTAVerified

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:

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

Papers

Showing 101150 of 167 papers

TitleStatusHype
FeatMatch: Feature-Based Augmentation for Semi-Supervised LearningCode1
Improving Face Recognition by Clustering Unlabeled Faces in the Wild0
Temporal Self-Ensembling Teacher for Semi-Supervised Object DetectionCode1
Consistency Regularization with Generative Adversarial Networks for Semi-Supervised Learning0
Unsupervised Learning of Visual Features by Contrasting Cluster AssignmentsCode2
Big Self-Supervised Models are Strong Semi-Supervised LearnersCode2
Building One-Shot Semi-supervised (BOSS) Learning up to Fully Supervised PerformanceCode1
Bootstrap your own latent: A new approach to self-supervised LearningCode1
SCAN: Learning to Classify Images without LabelsCode2
A Self-ensembling Framework for Semi-supervised Knee Cartilage Defects Assessment with Dual-ConsistencyCode1
Prototypical Contrastive Learning of Unsupervised RepresentationsCode1
DMT: Dynamic Mutual Training for Semi-Supervised LearningCode1
Milking CowMask for Semi-Supervised Image ClassificationCode0
Meta Pseudo LabelsCode1
A Simple Framework for Contrastive Learning of Visual RepresentationsCode2
Subspace Capsule NetworkCode1
FixMatch: Simplifying Semi-Supervised Learning with Consistency and ConfidenceCode2
batchboost: regularization for stabilizing training with resistance to underfitting & overfittingCode1
Semi-Supervised Learning with Normalizing FlowsCode0
SESS: Self-Ensembling Semi-Supervised 3D Object DetectionCode0
Triple Generative Adversarial NetworksCode0
RealMix: Towards Realistic Semi-Supervised Deep Learning AlgorithmsCode0
Self-Supervised Learning of Pretext-Invariant RepresentationsCode1
Flow Contrastive Estimation of Energy-Based ModelsCode1
ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation AnchoringCode1
EnAET: A Self-Trained framework for Semi-Supervised and Supervised Learning with Ensemble TransformationsCode0
Adversarial Transformations for Semi-Supervised Learning0
Dual Student: Breaking the Limits of the Teacher in Semi-supervised LearningCode0
Repetitive Reprediction Deep Decipher for Semi-Supervised LearningCode0
Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation0
Large Scale Adversarial Representation LearningCode1
Exploring Self-Supervised Regularization for Supervised and Semi-Supervised LearningCode0
Energy Models for Better Pseudo-Labels: Improving Semi-Supervised Classification with the 1-Laplacian Graph Energy0
Manifold Graph with Learned Prototypes for Semi-Supervised Image Classification0
Data-Efficient Image Recognition with Contrastive Predictive CodingCode0
Semi-Supervised Learning by Augmented Distribution AlignmentCode0
S4L: Self-Supervised Semi-Supervised LearningCode0
MixMatch: A Holistic Approach to Semi-Supervised LearningCode1
Semi-supervised Sequence-to-sequence ASR using Unpaired Speech and Text0
Unsupervised Data Augmentation for Consistency TrainingCode1
Deep Sparse Representation-based ClassificationCode0
Interpolation Consistency Training for Semi-Supervised LearningCode0
Semi-Supervised Deep Learning with MemoryCode0
Representation Learning with Contrastive Predictive CodingCode1
Two Methods for Domain Adaptation of Bilingual Tasks: Delightfully Simple and Broadly ApplicableCode0
There Are Many Consistent Explanations of Unlabeled Data: Why You Should AverageCode0
Unsupervised Feature Learning via Non-Parametric Instance DiscriminationCode1
Unsupervised Learning using Pretrained CNN and Associative Memory Bank0
CapsuleGAN: Generative Adversarial Capsule NetworkCode0
Structured Generative Adversarial NetworksCode0
Show:102550
← PrevPage 3 of 4Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SimCLR (ResNet-50 4×)Top 5 Accuracy92.6Unverified
2Rotation + VAT + Ent. Min.Top 5 Accuracy91.23Unverified
3SimCLR (ResNet-50 2×)Top 5 Accuracy91.2Unverified
4Mean Teacher (ResNeXt-152)Top 5 Accuracy90.89Unverified
5OBoW (ResNet-50)Top 5 Accuracy90.7Unverified
6R2-D2 (ResNet-18)Top 5 Accuracy90.48Unverified
7FixMatchTop 5 Accuracy89.13Unverified
8UDATop 5 Accuracy88.52Unverified
9SimCLR (ResNet-50)Top 5 Accuracy87.8Unverified
10DHO (ViT-Large)Top 1 Accuracy85.9Unverified
#ModelMetricClaimedVerifiedStatus
1DHO (ViT-Large)Top 1 Accuracy84.6Unverified
2OBoW (ResNet-50)Top 5 Accuracy82.9Unverified
3DHO (ViT-Base)Top 1 Accuracy81.6Unverified
4REACT (ViT-Large)Top 1 Accuracy81.6Unverified
5Semi-SST (ViT-Huge)Top 1 Accuracy80.7Unverified
6Meta Co-TrainingTop 1 Accuracy80.7Unverified
7Super-SST (ViT-Huge)Top 1 Accuracy80.3Unverified
8Semi-ViT (ViT-Huge)Top 1 Accuracy80Unverified
9Semi-ViT (ViT-Large)Top 1 Accuracy77.3Unverified
10Super-SST (ViT-Small distilled)Top 1 Accuracy76.9Unverified
#ModelMetricClaimedVerifiedStatus
1Γ-modelPercentage error20.4Unverified
2GANPercentage error15.59Unverified
3Bad GANPercentage error14.41Unverified
4Triple-GAN-V2 (CNN-13, no aug)Percentage error12.41Unverified
5Pi ModelPercentage error12.16Unverified
6SESEMI SSL (ConvNet)Percentage error11.65Unverified
7VATPercentage error11.36Unverified
8GLOT-DRPercentage error10.6Unverified
9VAT+EntMinPercentage error10.55Unverified
10Triple-GAN-V2 (CNN-13)Percentage error10.01Unverified
#ModelMetricClaimedVerifiedStatus
1Ⅱ-ModelPercentage error39.19Unverified
2SESEMI SSL (ConvNet)Percentage error38.7Unverified
3Temporal ensemblingPercentage error38.65Unverified
4R2-D2 (CNN-13)Percentage error32.87Unverified
5Dual Student (480)Percentage error32.77Unverified
6UPS (CNN-13)Percentage error32Unverified
7SHOT-VAEPercentage error25.3Unverified
8LiDAMPercentage error23.22Unverified
9EnAET (WRN-28-2-Large)Percentage error22.92Unverified
10FixMatch (RA, WRN-28-8)Percentage error22.6Unverified
#ModelMetricClaimedVerifiedStatus
1Ⅱ-ModelPercentage error53.12Unverified
2MixUpPercentage error47.43Unverified
3MeanTeacherPercentage error47.32Unverified
4VATPercentage error36.03Unverified
5LiDAMPercentage error19.17Unverified
6MixMatchPercentage error11.08Unverified
7RealMixPercentage error9.79Unverified
8EnAETPercentage error7.6Unverified
9ReMixMatchPercentage error6.27Unverified
10FixMatch+CRPercentage error5.04Unverified