# Image Classification on ImageNet-C with Textures-C outliers 1.0 (test) Source: [Image Classification on ImageNet-C with Textures-C outliers 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-03-27T13:58:48.259Z Evaluation of standard Image Classification accuracy, AUC, and H-score performance on the specific Textures-C outlier set (version 1.0) derived from ImageNet-C, using the test split. 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-C with Textures-C outliers 1.0 (test) | | Metric | Accuracy | | 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 - [Accuracy](): Higher is better; unit: PERCENT. - [AUC](): Higher is better; unit: PERCENT. - [H-score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | STAMP + Hi-Vec | 46.8 | Not recorded | 68fa7a9c1e209131cea84373 | | STAMP | 46.5 | Not recorded | 68fa7a9c1e209131cea84373 | | EATA | 46.4 | Not recorded | 68fa7a9c1e209131cea84373 | | SAR + Hi-Vec | 46.2 | Not recorded | 68fa7a9c1e209131cea84373 | | SAR | 45.6 | Not recorded | 68fa7a9c1e209131cea84373 | | SoTTA | 41.8 | Not recorded | 68fa7a9c1e209131cea84373 | | Tent + Hi-Vec | 39.4 | Not recorded | 68fa7a9c1e209131cea84373 | | Tent | 39 | Not recorded | 68fa7a9c1e209131cea84373 | | RoTTA | 37 | Not recorded | 68fa7a9c1e209131cea84373 | | CoTTA | 34.2 | Not recorded | 68fa7a9c1e209131cea84373 | | BN Stats | 31.6 | Not recorded | 68fa7a9c1e209131cea84373 | | MRL | 18.4 | Not recorded | 68fa7a9c1e209131cea84373 | | Source | 18.2 | Not recorded | 68fa7a9c1e209131cea84373 | | OWTTT | 9.4 | Not recorded | 68fa7a9c1e209131cea84373 | ### STAMP + Hi-Vec Accuracy: 46.8. Result ID: 69c68cb647f34ce924b0c314. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### STAMP Accuracy: 46.5. Result ID: 69c68cb647f34ce924b0c311. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### EATA Accuracy: 46.4. Result ID: 69c68cb647f34ce924b0c30a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### SAR + Hi-Vec Accuracy: 46.2. Result ID: 69c68cb647f34ce924b0c313. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### SAR Accuracy: 45.6. Result ID: 69c68cb647f34ce924b0c310. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### SoTTA Accuracy: 41.8. Result ID: 69c68cb647f34ce924b0c30d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### Tent + Hi-Vec Accuracy: 39.4. Result ID: 69c68cb647f34ce924b0c312. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### Tent Accuracy: 39. Result ID: 69c68cb647f34ce924b0c30f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### RoTTA Accuracy: 37. Result ID: 69c68cb647f34ce924b0c30c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### CoTTA Accuracy: 34.2. Result ID: 69c68cb647f34ce924b0c30b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### BN Stats Accuracy: 31.6. Result ID: 69c68cb647f34ce924b0c309. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### MRL Accuracy: 18.4. Result ID: 69c68cb647f34ce924b0c308. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### Source Accuracy: 18.2. Result ID: 69c68cb647f34ce924b0c307. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### OWTTT Accuracy: 9.4. Result ID: 69c68cb647f34ce924b0c30e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.