# Image Classification on ImageNet-C with Places365-C outliers 1.0 (test) Source: [Image Classification on ImageNet-C with Places365-C outliers 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-03-27T13:58:48.223Z Evaluation of standard Image Classification performance using the test split of the ImageNet-C dataset corrupted specifically by Places365-C outliers (version 1.0). Metrics include ACC, AUC, and H-score. 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 Places365-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 | 46.9 | Not recorded | 68fa7a9c1e209131cea84373 | | EATA | 46.4 | Not recorded | 68fa7a9c1e209131cea84373 | | STAMP | 46.4 | Not recorded | 68fa7a9c1e209131cea84373 | | SAR + Hi-Vec | 45.3 | Not recorded | 68fa7a9c1e209131cea84373 | | SAR | 44.9 | Not recorded | 68fa7a9c1e209131cea84373 | | SoTTA | 41.7 | Not recorded | 68fa7a9c1e209131cea84373 | | RoTTA | 36.6 | Not recorded | 68fa7a9c1e209131cea84373 | | Tent + Hi-Vec | 35.4 | Not recorded | 68fa7a9c1e209131cea84373 | | Tent | 34.9 | Not recorded | 68fa7a9c1e209131cea84373 | | CoTTA | 33.8 | Not recorded | 68fa7a9c1e209131cea84373 | | BN Stats | 31.1 | Not recorded | 68fa7a9c1e209131cea84373 | | MRL | 18.4 | Not recorded | 68fa7a9c1e209131cea84373 | | Source | 18.2 | Not recorded | 68fa7a9c1e209131cea84373 | | OWTTT | 9.1 | Not recorded | 68fa7a9c1e209131cea84373 | ### STAMP + Hi-Vec Accuracy: 46.9. Result ID: 69c68cb647f34ce924b0c306. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### EATA Accuracy: 46.4. Result ID: 69c68cb647f34ce924b0c2fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### STAMP Accuracy: 46.4. Result ID: 69c68cb647f34ce924b0c303. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### SAR + Hi-Vec Accuracy: 45.3. Result ID: 69c68cb647f34ce924b0c305. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### SAR Accuracy: 44.9. Result ID: 69c68cb647f34ce924b0c302. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### SoTTA Accuracy: 41.7. Result ID: 69c68cb647f34ce924b0c2ff. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### RoTTA Accuracy: 36.6. Result ID: 69c68cb647f34ce924b0c2fe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### Tent + Hi-Vec Accuracy: 35.4. Result ID: 69c68cb647f34ce924b0c304. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### Tent Accuracy: 34.9. Result ID: 69c68cb647f34ce924b0c301. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### CoTTA Accuracy: 33.8. Result ID: 69c68cb647f34ce924b0c2fd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### BN Stats Accuracy: 31.1. Result ID: 69c68cb647f34ce924b0c2fb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### MRL Accuracy: 18.4. Result ID: 69c68cb647f34ce924b0c2fa. [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: 69c68cb647f34ce924b0c2f9. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### OWTTT Accuracy: 9.1. Result ID: 69c68cb647f34ce924b0c300. [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.