# Image Classification on CIFAR-10 (test) (Robustness Symm 0.2 & 0.5) Source: [Image Classification on CIFAR-10 (test) (Robustness Symm 0.2 & 0.5)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:27.519Z Evaluation of Image Classification model performance on the CIFAR-10 test set, reporting accuracy under specific symmetry/perturbation levels (0.2 and 0.5). 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 (Symm 0.2) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 (Symm 0.2)](): Higher is better; unit: PERCENT. - [Accuracy (Symm 0.5)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Symm 0.2) | Result date | Report paper | | --- | --- | --- | --- | | CORES2 | 95.9 | Not recorded | 68fa698f1e209131cea22a5b | | DivideMix | 95.7 | Not recorded | 68fa698f1e209131cea22a5b | | M-correction | 93.8 | Not recorded | 68fa698f1e209131cea22a5b | | Mixup | 92.3 | Not recorded | 68fa698f1e209131cea22a5b | | P-correction | 92 | Not recorded | 68fa698f1e209131cea22a5b | | Meta-Learning | 92 | Not recorded | 68fa698f1e209131cea22a5b | | Co-teaching+ | 88.2 | Not recorded | 68fa698f1e209131cea22a5b | | Forward T | 83.1 | Not recorded | 68fa698f1e209131cea22a5b | | Bootstrap | 82.9 | Not recorded | 68fa698f1e209131cea22a5b | | CE | 82.7 | Not recorded | 68fa698f1e209131cea22a5b | ### CORES2 Accuracy (Symm 0.2): 95.9. Result ID: 698db6708b517eb433234421. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Pre-ResNet18"}. This record does not assert independent reproduction. ### DivideMix Accuracy (Symm 0.2): 95.7. Result ID: 698db6708b517eb433234420. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Pre-ResNet18"}. This record does not assert independent reproduction. ### M-correction Accuracy (Symm 0.2): 93.8. Result ID: 698db6708b517eb43323441f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Pre-ResNet18"}. This record does not assert independent reproduction. ### Mixup Accuracy (Symm 0.2): 92.3. Result ID: 698db6708b517eb43323441c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Pre-ResNet18"}. This record does not assert independent reproduction. ### P-correction Accuracy (Symm 0.2): 92. Result ID: 698db6708b517eb43323441d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Pre-ResNet18"}. This record does not assert independent reproduction. ### Meta-Learning Accuracy (Symm 0.2): 92. Result ID: 698db6708b517eb43323441e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Pre-ResNet18"}. This record does not assert independent reproduction. ### Co-teaching+ Accuracy (Symm 0.2): 88.2. Result ID: 698db6708b517eb43323441b. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Pre-ResNet18"}. This record does not assert independent reproduction. ### Forward T Accuracy (Symm 0.2): 83.1. Result ID: 698db6708b517eb43323441a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Pre-ResNet18"}. This record does not assert independent reproduction. ### Bootstrap Accuracy (Symm 0.2): 82.9. Result ID: 698db6708b517eb433234419. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Pre-ResNet18"}. This record does not assert independent reproduction. ### CE Accuracy (Symm 0.2): 82.7. Result ID: 698db6708b517eb433234418. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Pre-ResNet18"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.