# Image Classification on CIFAR-10 (test) (Noise Corruption Robustness) Source: [Image Classification on CIFAR-10 (test) (Noise Corruption Robustness)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:27.761Z Evaluation of Image Classification performance on the CIFAR-10 test set, specifically measuring accuracy under various levels of symmetric and asymmetric data corruption noise. 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) | CIFAR-10 (test) | | Metric | Accuracy (Symmetric 20% noise) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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 - [Accuracy (Symmetric 20% noise)](): Higher is better; unit: PERCENT. - [Accuracy (Symmetric 50% noise)](): Higher is better; unit: PERCENT. - [Accuracy (Symmetric 80% noise)](): Higher is better; unit: PERCENT. - [Accuracy (Symmetric 90% noise)](): Higher is better; unit: PERCENT. - [Accuracy (Asymmetric 40% noise)](): Higher is better; unit: PERCENT. - [Accuracy (Asymmetric 49% noise)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Symmetric 20% noise) | Result date | Report paper | | --- | --- | --- | --- | | LongReMix | 96.3 | Not recorded | 68fa6d5a1e209131cea39623 | | DivideMix | 96.1 | Not recorded | 68fa6d5a1e209131cea39623 | | LongReMix | 96 | Not recorded | 68fa6d5a1e209131cea39623 | | ELR+ | 95.8 | Not recorded | 68fa6d5a1e209131cea39623 | | DivideMix | 95.7 | Not recorded | 68fa6d5a1e209131cea39623 | | MixUp | 95.6 | Not recorded | 68fa6d5a1e209131cea39623 | | M-correction | 94 | Not recorded | 68fa6d5a1e209131cea39623 | | M-correction | 93.8 | Not recorded | 68fa6d5a1e209131cea39623 | | Meta-Learning | 92.9 | Not recorded | 68fa6d5a1e209131cea39623 | | MixUp | 92.3 | Not recorded | 68fa6d5a1e209131cea39623 | | Meta-Learning | 92 | Not recorded | 68fa6d5a1e209131cea39623 | | Coteaching+ | 89.5 | Not recorded | 68fa6d5a1e209131cea39623 | | Coteaching+ | 88.2 | Not recorded | 68fa6d5a1e209131cea39623 | | Cross-Entropy | 86.8 | Not recorded | 68fa6d5a1e209131cea39623 | | Cross-Entropy | 82.7 | Not recorded | 68fa6d5a1e209131cea39623 | ### LongReMix Accuracy (Symmetric 20% noise): 96.3. Result ID: 698f87de3a6c314849f9bb44. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Epoch selection":"Best","Backbone":"PRN18"}. This record does not assert independent reproduction. ### DivideMix Accuracy (Symmetric 20% noise): 96.1. Result ID: 698f87de3a6c314849f9bb41. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Epoch selection":"Best","Backbone":"PRN18"}. This record does not assert independent reproduction. ### LongReMix Accuracy (Symmetric 20% noise): 96. Result ID: 698f87de3a6c314849f9bb45. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Epoch selection":"Last","Backbone":"PRN18"}. This record does not assert independent reproduction. ### ELR+ Accuracy (Symmetric 20% noise): 95.8. Result ID: 698f87de3a6c314849f9bb43. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Epoch selection":"Best","Backbone":"PRN18"}. This record does not assert independent reproduction. ### DivideMix Accuracy (Symmetric 20% noise): 95.7. Result ID: 698f87de3a6c314849f9bb42. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Epoch selection":"Last","Backbone":"PRN18"}. This record does not assert independent reproduction. ### MixUp Accuracy (Symmetric 20% noise): 95.6. Result ID: 698f87de3a6c314849f9bb3b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Epoch selection":"Best","Backbone":"PRN18"}. This record does not assert independent reproduction. ### M-correction Accuracy (Symmetric 20% noise): 94. Result ID: 698f87de3a6c314849f9bb3f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Epoch selection":"Best","Backbone":"PRN18"}. This record does not assert independent reproduction. ### M-correction Accuracy (Symmetric 20% noise): 93.8. Result ID: 698f87de3a6c314849f9bb40. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Epoch selection":"Last","Backbone":"PRN18"}. This record does not assert independent reproduction. ### Meta-Learning Accuracy (Symmetric 20% noise): 92.9. Result ID: 698f87de3a6c314849f9bb3d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Epoch selection":"Best","Backbone":"PRN18"}. This record does not assert independent reproduction. ### MixUp Accuracy (Symmetric 20% noise): 92.3. Result ID: 698f87de3a6c314849f9bb3c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Epoch selection":"Last","Backbone":"PRN18"}. This record does not assert independent reproduction. ### Meta-Learning Accuracy (Symmetric 20% noise): 92. Result ID: 698f87de3a6c314849f9bb3e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Epoch selection":"Last","Backbone":"PRN18"}. This record does not assert independent reproduction. ### Coteaching+ Accuracy (Symmetric 20% noise): 89.5. Result ID: 698f87de3a6c314849f9bb39. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Epoch selection":"Best","Backbone":"PRN18"}. This record does not assert independent reproduction. ### Coteaching+ Accuracy (Symmetric 20% noise): 88.2. Result ID: 698f87de3a6c314849f9bb3a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Epoch selection":"Last","Backbone":"PRN18"}. This record does not assert independent reproduction. ### Cross-Entropy Accuracy (Symmetric 20% noise): 86.8. Result ID: 698f87de3a6c314849f9bb37. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Epoch selection":"Best","Backbone":"PRN18"}. This record does not assert independent reproduction. ### Cross-Entropy Accuracy (Symmetric 20% noise): 82.7. Result ID: 698f87de3a6c314849f9bb38. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Epoch selection":"Last","Backbone":"PRN18"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.