# Image Classification on ImageNet 10-class subset (test) Source: [Image Classification on ImageNet 10-class subset (test)]() Collection index: [llms.txt]() Data updated: 2026-02-27T12:06:53.704Z Evaluation of Image Classification performance on a specific 10-class subset of the ImageNet test set, reporting Certified Accuracy across various perturbation radii (epsilon values). 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) | ImageNet 10-class subset (test) | | Metric | Certified Accuracy (eps=0.00) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 4 of 4 | | 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 - [Certified Accuracy (eps=0.00)](): Higher is better; unit: PERCENT. - [Certified Accuracy (eps=0.125)](): Higher is better; unit: PERCENT. - [Certified Accuracy (eps=0.25)](): Higher is better; unit: PERCENT. - [Certified Accuracy (eps=0.375)](): Higher is better; unit: PERCENT. - [Certified Accuracy (eps=0.5)](): Higher is better; unit: PERCENT. - [Certified Accuracy (eps=0.75)](): Higher is better; unit: PERCENT. - [Certified Accuracy (eps=1)](): Higher is better; unit: PERCENT. - [Certified Accuracy (eps=1.50)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Certified Accuracy (eps=0.00) | Result date | Report paper | | --- | --- | --- | --- | | Feature-space Smoothing (FS) | 94.2 | Not recorded | 697300a9b2be0ed85a78cb9e | | Randomized Smoothing (RS) | 93.4 | Not recorded | 697300a9b2be0ed85a78cb9e | | Randomized Smoothing (RS) | 91.2 | Not recorded | 697300a9b2be0ed85a78cb9e | | Feature-space Smoothing (FS) | 91 | Not recorded | 697300a9b2be0ed85a78cb9e | ### Feature-space Smoothing (FS) Certified Accuracy (eps=0.00): 94.2. Result ID: 69a188cb35dfcabb00e7aef1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Smoothing":"FS","sigma":"0.25"}. This record does not assert independent reproduction. ### Randomized Smoothing (RS) Certified Accuracy (eps=0.00): 93.4. Result ID: 69a188cb35dfcabb00e7aef0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Smoothing":"RS","sigma":"0.25"}. This record does not assert independent reproduction. ### Randomized Smoothing (RS) Certified Accuracy (eps=0.00): 91.2. Result ID: 69a188cb35dfcabb00e7aef2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Smoothing":"RS","sigma":"0.50"}. This record does not assert independent reproduction. ### Feature-space Smoothing (FS) Certified Accuracy (eps=0.00): 91. Result ID: 69a188cb35dfcabb00e7aef3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Smoothing":"FS","sigma":"0.50"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.