# Image Classification on SVHN (Label Subset Error Rate) Source: [Image Classification on SVHN (Label Subset Error Rate)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:42:21.673Z Evaluation of standard Image Classification performance on the SVHN dataset, specifically measuring error rates when considering only subsets of 40, 250, or 1000 labels. 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 | | Metric | Error Rate (1000 labels) | | Unit | PERCENT | | Direction | Lower is better | | Results loaded | 14 of 14 | | 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 - [Error Rate (1000 labels)](): Lower is better; unit: PERCENT. - [Error Rate (40 labels)](): Lower is better; unit: PERCENT. - [Error Rate (250 labels)](): Lower is better; unit: PERCENT. ## Recorded results | Method | Error Rate (1000 labels) | Result date | Report paper | | --- | --- | --- | --- | | CoMatch + EPASS | 1.85 | Not recorded | 68fa70f11e209131cea4e324 | | UDA | 1.91 | Not recorded | 68fa70f11e209131cea4e324 | | CoMatch | 2.01 | Not recorded | 68fa70f11e209131cea4e324 | | FixMatch | 2.02 | Not recorded | 68fa70f11e209131cea4e324 | | AdaMatch | 2.02 | Not recorded | 68fa70f11e209131cea4e324 | | SimMatch + EPASS | 2.02 | Not recorded | 68fa70f11e209131cea4e324 | | SimMatch | 2.05 | Not recorded | 68fa70f11e209131cea4e324 | | Dash | 2.08 | Not recorded | 68fa70f11e209131cea4e324 | | SoftMatch | 2.09 | Not recorded | 68fa70f11e209131cea4e324 | | Fully-Supervised | 2.13 | Not recorded | 68fa70f11e209131cea4e324 | | MixMatch | 5.01 | Not recorded | 68fa70f11e209131cea4e324 | | ReMixMatch | 5.36 | Not recorded | 68fa70f11e209131cea4e324 | | FreeMatch | 7.56 | Not recorded | 68fa70f11e209131cea4e324 | | FlexMatch | 7.9 | Not recorded | 68fa70f11e209131cea4e324 | ### CoMatch + EPASS Error Rate (1000 labels): 1.85. Result ID: 699165213a6c31484907db2a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### UDA Error Rate (1000 labels): 1.91. Result ID: 699165213a6c31484907db1f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CoMatch Error Rate (1000 labels): 2.01. Result ID: 699165213a6c31484907db25. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### FixMatch Error Rate (1000 labels): 2.02. Result ID: 699165213a6c31484907db22. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### AdaMatch Error Rate (1000 labels): 2.02. Result ID: 699165213a6c31484907db27. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SimMatch + EPASS Error Rate (1000 labels): 2.02. Result ID: 699165213a6c31484907db2b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SimMatch Error Rate (1000 labels): 2.05. Result ID: 699165213a6c31484907db26. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Dash Error Rate (1000 labels): 2.08. Result ID: 699165213a6c31484907db24. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SoftMatch Error Rate (1000 labels): 2.09. Result ID: 699165213a6c31484907db29. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Fully-Supervised Error Rate (1000 labels): 2.13. Result ID: 699165213a6c31484907db2c. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MixMatch Error Rate (1000 labels): 5.01. Result ID: 699165213a6c31484907db20. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### ReMixMatch Error Rate (1000 labels): 5.36. Result ID: 699165213a6c31484907db21. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### FreeMatch Error Rate (1000 labels): 7.56. Result ID: 699165213a6c31484907db28. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### FlexMatch Error Rate (1000 labels): 7.9. Result ID: 699165213a6c31484907db23. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.