# Image Classification on Facescrub (inference) Source: [Image Classification on Facescrub (inference)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:30:28.790Z Evaluation of Image Classification performance on the inference split of the Facescrub dataset, reporting accuracy and MSE metrics. 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) | Facescrub (inference) | | Metric | Accuracy | | 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](): Higher is better; unit: PERCENT. - [MSE (Dec.)](): Lower is better; unit: SCALAR. - [MSE (GAN)](): Lower is better; unit: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | No\_defense | 86.69 | Not recorded | 68fa77c91e209131cea7556d | | Bottleneck | 85.12 | Not recorded | 68fa77c91e209131cea7556d | | Bottleneck+CEM | 85 | Not recorded | 68fa77c91e209131cea7556d | | DistCorr+CEM | 83.78 | Not recorded | 68fa77c91e209131cea7556d | | DistCorr | 83.42 | Not recorded | 68fa77c91e209131cea7556d | | Noise\_Nopeek | 82.06 | Not recorded | 68fa77c91e209131cea7556d | | Noise\_Nopeek+CEM | 81.96 | Not recorded | 68fa77c91e209131cea7556d | | Noise\_ARL+CEM | 80.33 | Not recorded | 68fa77c91e209131cea7556d | | Noise\_ARL | 80.14 | Not recorded | 68fa77c91e209131cea7556d | | PATROL+CEM | 79.88 | Not recorded | 68fa77c91e209131cea7556d | | ResSFL | 79.6 | Not recorded | 68fa77c91e209131cea7556d | | ResSFL+CEM | 79.54 | Not recorded | 68fa77c91e209131cea7556d | | Dropout | 79.3 | Not recorded | 68fa77c91e209131cea7556d | | Dropout+CEM | 79.19 | Not recorded | 68fa77c91e209131cea7556d | | PATROL | 79.18 | Not recorded | 68fa77c91e209131cea7556d | ### No\_defense Accuracy: 86.69. Result ID: 699569f43badfaffe65de6a8. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"VGG11"}. This record does not assert independent reproduction. ### Bottleneck Accuracy: 85.12. Result ID: 699569f43badfaffe65de6a9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"VGG11"}. This record does not assert independent reproduction. ### Bottleneck+CEM Accuracy: 85. Result ID: 699569f43badfaffe65de6aa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"VGG11"}. This record does not assert independent reproduction. ### DistCorr+CEM Accuracy: 83.78. Result ID: 699569f43badfaffe65de6ac. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"VGG11"}. This record does not assert independent reproduction. ### DistCorr Accuracy: 83.42. Result ID: 699569f43badfaffe65de6ab. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"VGG11"}. This record does not assert independent reproduction. ### Noise\_Nopeek Accuracy: 82.06. Result ID: 699569f43badfaffe65de6b3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"VGG11"}. This record does not assert independent reproduction. ### Noise\_Nopeek+CEM Accuracy: 81.96. Result ID: 699569f43badfaffe65de6b4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"VGG11"}. This record does not assert independent reproduction. ### Noise\_ARL+CEM Accuracy: 80.33. Result ID: 699569f43badfaffe65de6b6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"VGG11"}. This record does not assert independent reproduction. ### Noise\_ARL Accuracy: 80.14. Result ID: 699569f43badfaffe65de6b5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"VGG11"}. This record does not assert independent reproduction. ### PATROL+CEM Accuracy: 79.88. Result ID: 699569f43badfaffe65de6b0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"VGG11"}. This record does not assert independent reproduction. ### ResSFL Accuracy: 79.6. Result ID: 699569f43badfaffe65de6b1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"VGG11"}. This record does not assert independent reproduction. ### ResSFL+CEM Accuracy: 79.54. Result ID: 699569f43badfaffe65de6b2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"VGG11"}. This record does not assert independent reproduction. ### Dropout Accuracy: 79.3. Result ID: 699569f43badfaffe65de6ad. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"VGG11"}. This record does not assert independent reproduction. ### Dropout+CEM Accuracy: 79.19. Result ID: 699569f43badfaffe65de6ae. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"VGG11"}. This record does not assert independent reproduction. ### PATROL Accuracy: 79.18. Result ID: 699569f43badfaffe65de6af. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"VGG11"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.