# Image Classification on CIFAR-10 (Standard and Robust Accuracy) Source: [Image Classification on CIFAR-10 (Standard and Robust Accuracy)]() Collection index: [llms.txt]() Data updated: 2026-03-26T13:47:27.206Z Evaluation of Image Classification performance on CIFAR-10, reporting both standard nominal accuracy and a general measure of robustness accuracy. 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 | | Metric | Standard Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 9 of 9 | | 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 - [Standard Accuracy](): Higher is better; unit: PERCENT. - [Robust Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Standard Accuracy | Result date | Report paper | | --- | --- | --- | --- | | RCT-AF (β = 1) | 87.24 | Not recorded | 69c4bd7b0636e5bf4afc755c | | RCT-AF (β = 0) | 86.65 | Not recorded | 69c4bd7b0636e5bf4afc755c | | RCT-AF (β = 2) | 86.08 | Not recorded | 69c4bd7b0636e5bf4afc755c | | ReLU | 85.23 | Not recorded | 69c4bd7b0636e5bf4afc755c | | GELU | 84.88 | Not recorded | 69c4bd7b0636e5bf4afc755c | | Leaky ReLU | 84.52 | Not recorded | 69c4bd7b0636e5bf4afc755c | | Mish | 82.63 | Not recorded | 69c4bd7b0636e5bf4afc755c | | Swish | 82.53 | Not recorded | 69c4bd7b0636e5bf4afc755c | | ELU | 78.39 | Not recorded | 69c4bd7b0636e5bf4afc755c | ### RCT-AF (β = 1) Standard Accuracy: 87.24. Result ID: 69c5373547f34ce924aed9db. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Activation Function":"RCT-AF","β":"1","max \|σ''\|":"7.0","Backbone":"ResNet-18","Training Method":"DAJAT","Evaluation Protocol":"AutoAttack"}. This record does not assert independent reproduction. ### RCT-AF (β = 0) Standard Accuracy: 86.65. Result ID: 69c5373547f34ce924aed9da. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Activation Function":"RCT-AF","β":"0","max \|σ''\|":"7.0","Backbone":"ResNet-18","Training Method":"DAJAT","Evaluation Protocol":"AutoAttack"}. This record does not assert independent reproduction. ### RCT-AF (β = 2) Standard Accuracy: 86.08. Result ID: 69c5373547f34ce924aed9dc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Activation Function":"RCT-AF","β":"2","max \|σ''\|":"7.0","Backbone":"ResNet-18","Training Method":"DAJAT","Evaluation Protocol":"AutoAttack"}. This record does not assert independent reproduction. ### ReLU Standard Accuracy: 85.23. Result ID: 69c5373547f34ce924aed9d4. [Reporting paper]() Recorded evaluation configuration: {"Activation Function":"ReLU","max \|σ''\|":"∞","Backbone":"ResNet-18","Training Method":"DAJAT","Evaluation Protocol":"AutoAttack"}. This record does not assert independent reproduction. ### GELU Standard Accuracy: 84.88. Result ID: 69c5373547f34ce924aed9d7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Activation Function":"GELU","max \|σ''\|":"0.798","Backbone":"ResNet-18","Training Method":"DAJAT","Evaluation Protocol":"AutoAttack"}. This record does not assert independent reproduction. ### Leaky ReLU Standard Accuracy: 84.52. Result ID: 69c5373547f34ce924aed9d5. [Reporting paper]() Recorded evaluation configuration: {"Activation Function":"Leaky ReLU","max \|σ''\|":"∞","negative slope":"0.01","Backbone":"ResNet-18","Training Method":"DAJAT","Evaluation Protocol":"AutoAttack"}. This record does not assert independent reproduction. ### Mish Standard Accuracy: 82.63. Result ID: 69c5373547f34ce924aed9d9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Activation Function":"Mish","max \|σ''\|":"0.362","Backbone":"ResNet-18","Training Method":"DAJAT","Evaluation Protocol":"AutoAttack"}. This record does not assert independent reproduction. ### Swish Standard Accuracy: 82.53. Result ID: 69c5373547f34ce924aed9d8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Activation Function":"Swish","max \|σ''\|":"0.5","Backbone":"ResNet-18","Training Method":"DAJAT","Evaluation Protocol":"AutoAttack"}. This record does not assert independent reproduction. ### ELU Standard Accuracy: 78.39. Result ID: 69c5373547f34ce924aed9d6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Activation Function":"ELU","max \|σ''\|":"1.0","Backbone":"ResNet-18","Training Method":"DAJAT","Evaluation Protocol":"AutoAttack"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.