# Robust Image Classification on CIFAR-10 (val) (Noise Levels 20%-80%) Source: [Robust Image Classification on CIFAR-10 (val) (Noise Levels 20%-80%)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:26:48.661Z Evaluation of Image Classification model performance on the CIFAR-10 validation set under varying levels of data corruption/noise (20%, 40%, 60%, and 80%). 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 (val) | | Metric | Acc (20% noise) | | Unit | PERCENT | | Direction | Higher 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 - [Acc (20% noise)](): Higher is better; unit: PERCENT. - [Acc (40% noise)](): Higher is better; unit: PERCENT. - [Acc (60% noise)](): Higher is better; unit: PERCENT. - [Acc (80% noise)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Acc (20% noise) | Result date | Report paper | | --- | --- | --- | --- | | MentorMix | 95.6 | Not recorded | 68fa68321e209131cea1aab4 | | M-DYR-H | 94 | Not recorded | 68fa65d71e209131cea0cad4 | | Arazo et al. | 94 | Not recorded | 68fa68321e209131cea1aab4 | | Mixup | 94 | Not recorded | 68fa68321e209131cea1aab4 | | MD-DYR-SH | 93.8 | Not recorded | 68fa65d71e209131cea0cad4 | | Huang et al. | 92.6 | Not recorded | 68fa68321e209131cea1aab4 | | Jiang et al. (2018b) | 92 | Not recorded | 68fa65d71e209131cea0cad4 | | MentorNet | 92 | Not recorded | 68fa68321e209131cea1aab4 | | Zhang & Sabuncu | 89.7 | Not recorded | 68fa68321e209131cea1aab4 | | Chen et al. | 89.7 | Not recorded | 68fa68321e209131cea1aab4 | | Lee et al. | 87.1 | Not recorded | 68fa68321e209131cea1aab4 | | Ma et al. (2018) | 85.1 | Not recorded | 68fa65d71e209131cea0cad4 | | Wang et al. (2018b) | 81.4 | Not recorded | 68fa65d71e209131cea0cad4 | ### MentorMix Acc (20% noise): 95.6. Result ID: 698d61958b517eb433211223. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-32"}. This record does not assert independent reproduction. ### M-DYR-H Acc (20% noise): 94. Result ID: 698ccc368b517eb4331cd013. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"PRN-18"}. This record does not assert independent reproduction. ### Arazo et al. Acc (20% noise): 94. Result ID: 698d61958b517eb43321121c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Mixup Acc (20% noise): 94. Result ID: 698d61958b517eb433211222. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MD-DYR-SH Acc (20% noise): 93.8. Result ID: 698ccc368b517eb4331cd014. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"PRN-18"}. This record does not assert independent reproduction. ### Huang et al. Acc (20% noise): 92.6. Result ID: 698d61958b517eb433211220. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Jiang et al. (2018b) Acc (20% noise): 92. Result ID: 698ccc368b517eb4331cd00f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"WRN-101"}. This record does not assert independent reproduction. ### MentorNet Acc (20% noise): 92. Result ID: 698d61958b517eb433211221. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Zhang & Sabuncu Acc (20% noise): 89.7. Result ID: 698d61958b517eb43321121d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Chen et al. Acc (20% noise): 89.7. Result ID: 698d61958b517eb43321121f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Lee et al. Acc (20% noise): 87.1. Result ID: 698d61958b517eb43321121e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Ma et al. (2018) Acc (20% noise): 85.1. Result ID: 698ccc368b517eb4331cd010. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Architecture":"GCNN-12"}. This record does not assert independent reproduction. ### Wang et al. (2018b) Acc (20% noise): 81.4. Result ID: 698ccc368b517eb4331cd012. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"GCNN-7"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.