</> Code with Papers by Syntology

Datasets › SVHN

SVHN (Street View House Numbers)

Introduced in Reading digits in natural images with unsupervised feature learning archive 2025-07-28

Street View House Numbers (SVHN) is a digit classification benchmark dataset that contains 600,000 32×32 RGB images of printed digits (from 0 to 9) cropped from pictures of house number plates. The cropped images are centered in the digit of interest, but nearby digits and other distractors are kept in the image. SVHN has three sets: training, testing sets and an extra set with 530,000 images that are less difficult and can be used for helping with the training process.

Source: Reading Digits in Natural Images with Unsupervised Feature Learning Image Source: http://ufldl.stanford.edu/housenumbers/

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 12 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Image Classification SVHN E2E-M3 Percentage error 1.0 Rethinking Recurrent Neural Networks and Other... leonlha/e2e-3m 62 Compare
Semi-Supervised Image Classification SVHN, 1000 labels Meta Pseudo Labels (WRN-28-2) Accuracy 98.01 ± 0.07 Meta Pseudo Labels google-research/google-research +8 17 Compare
Semi-Supervised Image Classification SVHN, 250 Labels ShrinkMatch Accuracy 98.04 Shrinking Class Space for Enhanced Certainty in... LiheYoung/ShrinkMatch 15 Compare
Domain Adaptation SVHN-to-MNIST Mean teacher Accuracy 99.18 Self-ensembling for visual domain adaptation thuml/Transfer-Learning-Library +2 14 Compare
Semi-Supervised Image Classification SVHN, 500 Labels Triple-GAN-V2 (CNN-13) Accuracy 96.39 Triple Generative Adversarial Networks taufikxu/Triple-GAN 6 Compare
Semi-Supervised Image Classification SVHN, 40 Labels ShrinkMatch Percentage error 2.51 Shrinking Class Space for Enhanced Certainty in... LiheYoung/ShrinkMatch 5 Compare
Unsupervised Image Classification SVHN ACOL-GAR Acc 76.80 Learning Latent Representations in Neural Networks for... — 4 Compare
Anomaly Detection SVHN RCALAD Mean AUC 57.7 Spot The Odd One Out: Regularized Complete Cycle... zahradehghanian97/rcalad 1 Compare
Novel Class Discovery SVHN AutoNovel Clustering Accuracy 0.954 AutoNovel: Automatically Discovering and Learning Novel... k-han/AutoNovel 1 Compare
Semi-Supervised Image Classification SVHN, 2000 Labels MixMatch Accuracy 96.96 MixMatch: A Holistic Approach to Semi-Supervised Learning google-research/mixmatch +29 1 Compare
Semi-Supervised Image Classification SVHN, 4000 Labels MixMatch Accuracy 97.11 MixMatch: A Holistic Approach to Semi-Supervised Learning google-research/mixmatch +29 1 Compare
Sparse Representation-based Classification SVHN DSRC Accuracy 67.75 Deep Sparse Representation-based Classification mahdiabavisani/DSRC 1 Compare

Papers archive 2025-07-28

30 shown of 88 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 3,406. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning 1 2 13 Aug 2023 ran 1 of 2 samples (1 unverified)
FACT: Federated Adversarial Cross Training 1 1 1 Jun 2023 not harvested
Spot The Odd One Out: Regularized Complete Cycle Consistent Anomaly Detector GAN 1 1 16 Apr 2023 not harvested
WaveMix-Lite: A Resource-efficient Neural Network for Image Analysis 1 1 13 Oct 2022 not harvested
Unsupervised domain adaptation using feature aligned maximum classifier discrepancy 0 1 3 Oct 2022 not harvested
Automatic Data Augmentation via Invariance-Constrained Learning 1 1 29 Sep 2022 ran 0 of 1 samples (1 unverified)
Connection Reduction of DenseNet for Image Recognition 1 1 2 Aug 2022 not harvested
Benchopt: Reproducible, efficient and collaborative optimization benchmarks 3 1 27 Jun 2022 ran 0 of 10 samples (10 unverified)
WaveMix: A Resource-efficient Neural Network for Image Analysis 1 1 28 May 2022 not harvested
EXACT: How to Train Your Accuracy 2 1 19 May 2022 not harvested
DoubleMatch: Improving Semi-Supervised Learning with Self-Supervision 1 3 11 May 2022 not harvested
Efficient Convolutional Neural Networks on Raspberry Pi for Image Classification 1 1 2 Apr 2022 ran 1 of 1 samples (0 unverified)
MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularization 1 2 27 Mar 2022 not harvested
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision 1 1 16 Feb 2022 not harvested
Preventing Manifold Intrusion with Locality: Local Mixup 1 1 12 Jan 2022 not harvested
ThreshNet: An Efficient DenseNet Using Threshold Mechanism to Reduce Connections 1 1 9 Jan 2022 not harvested
AutoNovel: Automatically Discovering and Learning Novel Visual Categories 1 1 29 Jun 2021 not harvested
Boosting the Performance of Semi-Supervised Learning with Unsupervised Clustering 1 2 1 Dec 2020 not harvested
Regularizing Neural Networks via Adversarial Model Perturbation 1 2 10 Oct 2020 ran 0 of 12 samples (12 unverified)
Rethinking Recurrent Neural Networks and Other Improvements for Image Classification 1 1 30 Jul 2020 not harvested
Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment 1 2 23 Jun 2020 ran 0 of 1 samples (1 unverified)
Deep Transformation-Invariant Clustering 1 1 19 Jun 2020 ran 1 of 10 samples (9 unverified)
Meta Pseudo Labels 9 1 23 Mar 2020 ran 5 of 14 samples (9 unverified)
Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation 3 1 20 Feb 2020 ran 2 of 2 samples (0 unverified; 2 pointer-only for licence)
Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods 1 1 24 Jan 2020 not harvested
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence 26 2 21 Jan 2020 ran 50 of 74 samples (24 unverified; 14 pointer-only for licence)
Triple Generative Adversarial Networks 1 6 20 Dec 2019 ran 0 of 8 samples (8 unverified)
RealMix: Towards Realistic Semi-Supervised Deep Learning Algorithms 2 1 18 Dec 2019 ran 0 of 3 samples (3 unverified)
Flow Contrastive Estimation of Energy-Based Models 2 2 2 Dec 2019 ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation 1 1 28 Nov 2019 not harvested

The full list of 88 is in the JSON twin.

Dataset loaders archive 2025-07-28

huggingface.co/datasets/ufldl-stanford/svhnhuggingface/datasetstfpytorchjax
huggingface.co/datasets/svhnhuggingface/datasetstfpytorchjax
pytorch.org/vision/stable/generated/torchvision.datasets.SVHN.htmlpytorch/visionpytorch
datasets.activeloop.ai/docs/ml/datasets/the-street-view-house-numbers-svhn-dataset/activeloopai/deeplaketfpytorch
www.tensorflow.org/datasets/catalog/svhn_croppedtensorflow/datasetstfjax
gas.graviti.com/dataset/graviti/SVHNGraviti-AI/datasetstfpytorch
gitlab.com/afagarap/pt-datasetspytorch

7 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Image ClassificationAnomaly DetectionDomain AdaptationSemi-Supervised Image ClassificationUnsupervised Image ClassificationNovel Class DiscoverySparse Representation-based Classification

License archive 2025-07-28

CC

Modalities archive 2025-07-28

Images

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • svhn,1000
  • SVHN, 4000 Labels
  • SVHN, 2000 Labels
  • SVHN-to-MNIST
  • SVHN, 500 Labels
  • SVHN, 40 Labels
  • SVHN, 250 Labels
  • SVHN, 1000 labels
  • SVHN

9 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections