# Image Classification on ImageNet-1k Corrupt Source: [Image Classification on ImageNet-1k Corrupt]() Collection index: [llms.txt]() Data updated: 2026-06-23T10:14:23.916Z Evaluation of Image Classification robustness on the ImageNet-1k dataset subjected to various corruption types. 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-1k Corrupt | | 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. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | CE | 30.61 | Not recorded | 68fa76a61e209131cea6e28f | | LN | 30.13 | Not recorded | 68fa76a61e209131cea6e28f | | HEM- | 29.14 | Not recorded | 68fa76a61e209131cea6e28f | | LN | 28.01 | Not recorded | 68fa76a61e209131cea6e28f | | LN | 25.27 | Not recorded | 68fa76a61e209131cea6e28f | | CE | 24.8 | Not recorded | 68fa76a61e209131cea6e28f | | HEM- | 24.71 | Not recorded | 68fa76a61e209131cea6e28f | | CE | 24.53 | Not recorded | 68fa76a61e209131cea6e28f | | HEM- | 22.81 | Not recorded | 68fa76a61e209131cea6e28f | | MM | 22.36 | Not recorded | 68fa76a61e209131cea6e28f | | MM | 21 | Not recorded | 68fa76a61e209131cea6e28f | | MM | 8.3 | Not recorded | 68fa76a61e209131cea6e28f | | DICE | 6.56 | Not recorded | 68fa76a61e209131cea6e28f | | DICE | 3.71 | Not recorded | 68fa76a61e209131cea6e28f | | DICE | 0.96 | Not recorded | 68fa76a61e209131cea6e28f | ### CE Accuracy: 30.61. Result ID: 6a3a5c6dfbc373592c369411. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction. ### LN Accuracy: 30.13. Result ID: 6a3a5c6dfbc373592c369412. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction. ### HEM- Accuracy: 29.14. Result ID: 6a3a5c6dfbc373592c369415. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction. ### LN Accuracy: 28.01. Result ID: 6a3a5c6dfbc373592c369417. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"SwinT"}. This record does not assert independent reproduction. ### LN Accuracy: 25.27. Result ID: 6a3a5c6dfbc373592c36941c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction. ### CE Accuracy: 24.8. Result ID: 6a3a5c6dfbc373592c36941b. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction. ### HEM- Accuracy: 24.71. Result ID: 6a3a5c6dfbc373592c36941a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"SwinT"}. This record does not assert independent reproduction. ### CE Accuracy: 24.53. Result ID: 6a3a5c6dfbc373592c369416. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"SwinT"}. This record does not assert independent reproduction. ### HEM- Accuracy: 22.81. Result ID: 6a3a5c6dfbc373592c36941f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction. ### MM Accuracy: 22.36. Result ID: 6a3a5c6dfbc373592c369414. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction. ### MM Accuracy: 21. Result ID: 6a3a5c6dfbc373592c36941e. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction. ### MM Accuracy: 8.3. Result ID: 6a3a5c6dfbc373592c369419. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"SwinT"}. This record does not assert independent reproduction. ### DICE Accuracy: 6.56. Result ID: 6a3a5c6dfbc373592c369418. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"SwinT"}. This record does not assert independent reproduction. ### DICE Accuracy: 3.71. Result ID: 6a3a5c6dfbc373592c36941d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction. ### DICE Accuracy: 0.96. Result ID: 6a3a5c6dfbc373592c369413. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.