# Image Classification on MNIST-M unbalanced + flexible + adversarial setting (test) Source: [Image Classification on MNIST-M unbalanced + flexible + adversarial setting (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:00:56.747Z Evaluation of Image Classification performance on a specific, robust test configuration of the MNIST-M domain adaptation dataset, reporting domain robustness metrics. 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) | MNIST-M unbalanced + flexible + adversarial setting (test) | | Metric | Random Baseline Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 - [Random Baseline Accuracy](): Higher is better; unit: PERCENT. - [DR 0.5 Accuracy](): Higher is better; unit: PERCENT. - [DR 0.6 Accuracy](): Higher is better; unit: PERCENT. - [DR 0.7 Accuracy](): Higher is better; unit: PERCENT. - [DR 0.8 Accuracy](): Higher is better; unit: PERCENT. - [DR 0.9 Accuracy](): Higher is better; unit: PERCENT. - [DR 0.95 Accuracy](): Higher is better; unit: PERCENT. - [Average Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Random Baseline Accuracy | Result date | Report paper | | --- | --- | --- | --- | | StableNet | 97.35 | Not recorded | 68fa69cd1e209131cea24276 | | JiGen | 97.18 | Not recorded | 68fa69cd1e209131cea24276 | | RSC | 96.94 | Not recorded | 68fa69cd1e209131cea24276 | | CNNs | 96.93 | Not recorded | 68fa69cd1e209131cea24276 | | DG-MMLD | 96.89 | Not recorded | 68fa69cd1e209131cea24276 | | M-ADA | 95.92 | Not recorded | 68fa69cd1e209131cea24276 | ### StableNet Random Baseline Accuracy: 97.35. Result ID: 698de57bffc3901de0996e79. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"setting":"unbalanced + flexible + adversarial"}. This record does not assert independent reproduction. ### JiGen Random Baseline Accuracy: 97.18. Result ID: 698de57bffc3901de0996e74. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"setting":"unbalanced + flexible + adversarial"}. This record does not assert independent reproduction. ### RSC Random Baseline Accuracy: 96.94. Result ID: 698de57bffc3901de0996e77. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"setting":"unbalanced + flexible + adversarial"}. This record does not assert independent reproduction. ### CNNs Random Baseline Accuracy: 96.93. Result ID: 698de57bffc3901de0996e78. [Reporting paper]() Recorded evaluation configuration: {"setting":"unbalanced + flexible + adversarial"}. This record does not assert independent reproduction. ### DG-MMLD Random Baseline Accuracy: 96.89. Result ID: 698de57bffc3901de0996e76. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"setting":"unbalanced + flexible + adversarial"}. This record does not assert independent reproduction. ### M-ADA Random Baseline Accuracy: 95.92. Result ID: 698de57bffc3901de0996e75. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"setting":"unbalanced + flexible + adversarial"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.