# Image Classification on SVHN (test) (Top-1 Error Rate) Source: [Image Classification on SVHN (test) (Top-1 Error Rate)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:07:19.609Z Evaluation of standard Image Classification performance on the test split of the SVHN dataset, reporting the Top-1 error rate. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Image Classification | | Dataset (including any stated split) | SVHN (test) | | Metric | Top-1 Error Rate | | Unit | PERCENT | | Direction | Lower is better | | Results loaded | 31 of 31 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Top-1 Error Rate](): Lower is better; unit: PERCENT. ## Recorded results | Method | Top-1 Error Rate | Result date | Report paper | | --- | --- | --- | --- | | Dash (RA) | 2.03 | Not recorded | 68fa6aa61e209131cea2970c | | Dash (CTA) | 2.14 | Not recorded | 68fa6aa61e209131cea2970c | | Dash (RA) | 2.17 | Not recorded | 68fa6aa61e209131cea2970c | | FixMatch (RA) | 2.28 | Not recorded | 68fa6aa61e209131cea2970c | | RYS (UDA) | 2.32 | Not recorded | 68fa6aa61e209131cea2970c | | RYS (FixMatch) | 2.34 | Not recorded | 68fa6aa61e209131cea2970c | | FixMatch (CTA) | 2.36 | Not recorded | 68fa6aa61e209131cea2970c | | Dash (CTA) | 2.38 | Not recorded | 68fa6aa61e209131cea2970c | | RYS (UDA) | 2.45 | Not recorded | 68fa6aa61e209131cea2970c | | UDA | 2.46 | Not recorded | 68fa6aa61e209131cea2970c | | FixMatch (RA) | 2.48 | Not recorded | 68fa6aa61e209131cea2970c | | RYS (FixMatch) | 2.63 | Not recorded | 68fa6aa61e209131cea2970c | | FixMatch (CTA) | 2.64 | Not recorded | 68fa6aa61e209131cea2970c | | ReMixMatch | 2.65 | Not recorded | 68fa6aa61e209131cea2970c | | ReMixMatch | 2.92 | Not recorded | 68fa6aa61e209131cea2970c | | Dash (RA) | 3.03 | Not recorded | 68fa6aa61e209131cea2970c | | Dash (CTA) | 3.14 | Not recorded | 68fa6aa61e209131cea2970c | | ReMixMatch | 3.34 | Not recorded | 68fa6aa61e209131cea2970c | | Mean Teacher | 3.42 | Not recorded | 68fa6aa61e209131cea2970c | | MixMatch | 3.5 | Not recorded | 68fa6aa61e209131cea2970c | | Mean Teacher | 3.57 | Not recorded | 68fa6aa61e209131cea2970c | | FixMatch (RA) | 3.96 | Not recorded | 68fa6aa61e209131cea2970c | | MixMatch | 3.98 | Not recorded | 68fa6aa61e209131cea2970c | | UDA | 5.69 | Not recorded | 68fa6aa61e209131cea2970c | | Pi-Model | 7.54 | Not recorded | 68fa6aa61e209131cea2970c | | FixMatch (CTA) | 7.65 | Not recorded | 68fa6aa61e209131cea2970c | | Pseudo-Labeling | 9.94 | Not recorded | 68fa6aa61e209131cea2970c | | Pi-Model | 18.96 | Not recorded | 68fa6aa61e209131cea2970c | | Pseudo-Labeling | 20.21 | Not recorded | 68fa6aa61e209131cea2970c | | MixMatch | 42.55 | Not recorded | 68fa6aa61e209131cea2970c | | UDA | 52.63 | Not recorded | 68fa6aa61e209131cea2970c | ### Dash (RA) Top-1 Error Rate: 2.03. Result ID: 699ac9465698665ec457bf26. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Number of labels":"1000","Backbone":"Wide ResNet-28-2","Augmentation strategy":"RandAugment"}. This record does not assert independent reproduction. ### Dash (CTA) Top-1 Error Rate: 2.14. Result ID: 699ac9465698665ec457bf20. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Number of labels":"1000","Backbone":"Wide ResNet-28-2","Augmentation strategy":"CTAugment"}. This record does not assert independent reproduction. ### Dash (RA) Top-1 Error Rate: 2.17. Result ID: 699ac9465698665ec457bf25. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Number of labels":"250","Backbone":"Wide ResNet-28-2","Augmentation strategy":"RandAugment"}. This record does not assert independent reproduction. ### FixMatch (RA) Top-1 Error Rate: 2.28. Result ID: 699ac9465698665ec457bf23. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"1000","Backbone":"Wide ResNet-28-2","Augmentation strategy":"RandAugment"}. This record does not assert independent reproduction. ### RYS (UDA) Top-1 Error Rate: 2.32. Result ID: 699ac9465698665ec457bf18. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"1000","Backbone":"Wide ResNet-28-2"}. This record does not assert independent reproduction. ### RYS (FixMatch) Top-1 Error Rate: 2.34. Result ID: 699ac9465698665ec457bf1a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"1000","Backbone":"Wide ResNet-28-2"}. This record does not assert independent reproduction. ### FixMatch (CTA) Top-1 Error Rate: 2.36. Result ID: 699ac9465698665ec457bf1d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"1000","Backbone":"Wide ResNet-28-2","Augmentation strategy":"CTAugment"}. This record does not assert independent reproduction. ### Dash (CTA) Top-1 Error Rate: 2.38. Result ID: 699ac9465698665ec457bf1f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Number of labels":"250","Backbone":"Wide ResNet-28-2","Augmentation strategy":"CTAugment"}. This record does not assert independent reproduction. ### RYS (UDA) Top-1 Error Rate: 2.45. Result ID: 699ac9465698665ec457bf17. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"250","Backbone":"Wide ResNet-28-2"}. This record does not assert independent reproduction. ### UDA Top-1 Error Rate: 2.46. Result ID: 699ac9465698665ec457bf13. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"1000","Backbone":"Wide ResNet-28-2"}. This record does not assert independent reproduction. ### FixMatch (RA) Top-1 Error Rate: 2.48. Result ID: 699ac9465698665ec457bf22. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"250","Backbone":"Wide ResNet-28-2","Augmentation strategy":"RandAugment"}. This record does not assert independent reproduction. ### RYS (FixMatch) Top-1 Error Rate: 2.63. Result ID: 699ac9465698665ec457bf19. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"250","Backbone":"Wide ResNet-28-2"}. This record does not assert independent reproduction. ### FixMatch (CTA) Top-1 Error Rate: 2.64. Result ID: 699ac9465698665ec457bf1c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"250","Backbone":"Wide ResNet-28-2","Augmentation strategy":"CTAugment"}. This record does not assert independent reproduction. ### ReMixMatch Top-1 Error Rate: 2.65. Result ID: 699ac9465698665ec457bf16. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"1000","Backbone":"Wide ResNet-28-2"}. This record does not assert independent reproduction. ### ReMixMatch Top-1 Error Rate: 2.92. Result ID: 699ac9465698665ec457bf15. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"250","Backbone":"Wide ResNet-28-2"}. This record does not assert independent reproduction. ### Dash (RA) Top-1 Error Rate: 3.03. Result ID: 699ac9465698665ec457bf24. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Number of labels":"40","Backbone":"Wide ResNet-28-2","Augmentation strategy":"RandAugment"}. This record does not assert independent reproduction. ### Dash (CTA) Top-1 Error Rate: 3.14. Result ID: 699ac9465698665ec457bf1e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Number of labels":"40","Backbone":"Wide ResNet-28-2","Augmentation strategy":"CTAugment"}. This record does not assert independent reproduction. ### ReMixMatch Top-1 Error Rate: 3.34. Result ID: 699ac9465698665ec457bf14. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"40","Backbone":"Wide ResNet-28-2"}. This record does not assert independent reproduction. ### Mean Teacher Top-1 Error Rate: 3.42. Result ID: 699ac9465698665ec457bf0d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"1000","Backbone":"Wide ResNet-28-2"}. This record does not assert independent reproduction. ### MixMatch Top-1 Error Rate: 3.5. Result ID: 699ac9465698665ec457bf10. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"1000","Backbone":"Wide ResNet-28-2"}. This record does not assert independent reproduction. ### Mean Teacher Top-1 Error Rate: 3.57. Result ID: 699ac9465698665ec457bf0c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"250","Backbone":"Wide ResNet-28-2"}. This record does not assert independent reproduction. ### FixMatch (RA) Top-1 Error Rate: 3.96. Result ID: 699ac9465698665ec457bf21. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"40","Backbone":"Wide ResNet-28-2","Augmentation strategy":"RandAugment"}. This record does not assert independent reproduction. ### MixMatch Top-1 Error Rate: 3.98. Result ID: 699ac9465698665ec457bf0f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"250","Backbone":"Wide ResNet-28-2"}. This record does not assert independent reproduction. ### UDA Top-1 Error Rate: 5.69. Result ID: 699ac9465698665ec457bf12. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"250","Backbone":"Wide ResNet-28-2"}. This record does not assert independent reproduction. ### Pi-Model Top-1 Error Rate: 7.54. Result ID: 699ac9465698665ec457bf09. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"1000","Backbone":"Wide ResNet-28-2"}. This record does not assert independent reproduction. ### FixMatch (CTA) Top-1 Error Rate: 7.65. Result ID: 699ac9465698665ec457bf1b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"40","Backbone":"Wide ResNet-28-2","Augmentation strategy":"CTAugment"}. This record does not assert independent reproduction. ### Pseudo-Labeling Top-1 Error Rate: 9.94. Result ID: 699ac9465698665ec457bf0b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"1000","Backbone":"Wide ResNet-28-2"}. This record does not assert independent reproduction. ### Pi-Model Top-1 Error Rate: 18.96. Result ID: 699ac9465698665ec457bf08. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"250","Backbone":"Wide ResNet-28-2"}. This record does not assert independent reproduction. ### Pseudo-Labeling Top-1 Error Rate: 20.21. Result ID: 699ac9465698665ec457bf0a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"250","Backbone":"Wide ResNet-28-2"}. This record does not assert independent reproduction. ### MixMatch Top-1 Error Rate: 42.55. Result ID: 699ac9465698665ec457bf0e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"40","Backbone":"Wide ResNet-28-2"}. This record does not assert independent reproduction. ### UDA Top-1 Error Rate: 52.63. Result ID: 699ac9465698665ec457bf11. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of labels":"40","Backbone":"Wide ResNet-28-2"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.