Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

SVHN dataset and benchmarks – Page 10 · SOTA2 Research

Research Datasets

SVHN

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Out-of-Distribution Detection

SVHN

84.1AUROC (LSUN)

5

Image Classification

SVHN (test)

96.37Accuracy

5

Image Classification

SVHN (test)

1.05Expected ||∇f(x)||^2

5

Supervised Domain Adaptation

SVHN → MNIST (test)

96.5Macro Accuracy

5

Image Classification

SVHN 500 labels (test)

3.61Error Rate

5

Image Classification

SVHN Split

98.3Accuracy (T1)

5

SVHN (test)

49.05Accuracy

5

Importance Learning

SVHN 50% label noise (test)

89.8Test Accuracy

5

Importance Learning

SVHN 25% label noise (test)

91.1Test Accuracy

5

Adversarial Robustness

SVHN

55.53Robust Accuracy (L1, eps=12)

4

Image Reconstruction

SVHN

0.09RMSE

4

Image Classification

SVHN

91.3PGD Accuracy

4

Single-class unlearning

SVHN

98.71FA

4

Out-of-Distribution Detection

SVHN

90.68AUC

4

Image Classification

SVHN (Non-IID 2)

89.34Accuracy

4

Image Classification

SVHN (Non-IID 1)

90.6Accuracy

4

Image Classification

SVHN (IID)

92.1Accuracy

4

Image Classification

SVHN

95.4Clean Accuracy

4

Backdoor Attack

SVHN (test)

0.937Accuracy

4

Image Classification

SVHN 25 labels per class

98.2Accuracy

4

Image Classification

SVHN 4 labels per class

98.2Accuracy (Seed 0)

4

Incremental Learning

SVHN 5-task incremental setting (test)

95.81Accuracy

4

Adversarial Attack

SVHN (test)

0Clean Accuracy

4

Attack Success Rate

SVHN (test)

0Clean Success Rate

4

Robust Accuracy

SVHN

95.4Accuracy (Clean)

4

Page 10 of 13

Popular tasks

Image Classification Out-of-Distribution Detection Machine Unlearning Image Generation OOD Detection

Follow for updates

Join SOTA2 Contact