# Image Classification on CIFAR100 Corrupt Source: [Image Classification on CIFAR100 Corrupt]() Collection index: [llms.txt]() Data updated: 2026-06-23T10:14:23.811Z Evaluation of Image Classification performance on the CIFAR-100 dataset subjected to corruption. 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) | CIFAR100 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 | 50.71 | Not recorded | 68fa76a61e209131cea6e28f | | LN | 50.7 | Not recorded | 68fa76a61e209131cea6e28f | | CE | 50.27 | Not recorded | 68fa76a61e209131cea6e28f | | LN | 49.9 | Not recorded | 68fa76a61e209131cea6e28f | | HEM- | 49.84 | Not recorded | 68fa76a61e209131cea6e28f | | HEM- | 49.22 | Not recorded | 68fa76a61e209131cea6e28f | | MM | 45.95 | Not recorded | 68fa76a61e209131cea6e28f | | MM | 45.2 | Not recorded | 68fa76a61e209131cea6e28f | | DICE | 44.81 | Not recorded | 68fa76a61e209131cea6e28f | | HEM- | 33.33 | Not recorded | 68fa76a61e209131cea6e28f | | LN | 33.11 | Not recorded | 68fa76a61e209131cea6e28f | | CE | 32.31 | Not recorded | 68fa76a61e209131cea6e28f | | MM | 26.17 | Not recorded | 68fa76a61e209131cea6e28f | | DICE | 15.35 | Not recorded | 68fa76a61e209131cea6e28f | | DICE | 2.03 | Not recorded | 68fa76a61e209131cea6e28f | ### CE Accuracy: 50.71. Result ID: 6a3a5c6dfbc373592c3693a3. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"PARN18"}. This record does not assert independent reproduction. ### LN Accuracy: 50.7. Result ID: 6a3a5c6dfbc373592c3693a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"PARN18"}. This record does not assert independent reproduction. ### CE Accuracy: 50.27. Result ID: 6a3a5c6dfbc373592c36939e. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### LN Accuracy: 49.9. Result ID: 6a3a5c6dfbc373592c36939f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### HEM- Accuracy: 49.84. Result ID: 6a3a5c6dfbc373592c3693a7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"PARN18"}. This record does not assert independent reproduction. ### HEM- Accuracy: 49.22. Result ID: 6a3a5c6dfbc373592c3693a2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### MM Accuracy: 45.95. Result ID: 6a3a5c6dfbc373592c3693a6. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"PARN18"}. This record does not assert independent reproduction. ### MM Accuracy: 45.2. Result ID: 6a3a5c6dfbc373592c3693a1. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### DICE Accuracy: 44.81. Result ID: 6a3a5c6dfbc373592c3693a0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction. ### HEM- Accuracy: 33.33. Result ID: 6a3a5c6dfbc373592c36939d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MobileNetL"}. This record does not assert independent reproduction. ### LN Accuracy: 33.11. Result ID: 6a3a5c6dfbc373592c36939a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"MobileNetL"}. This record does not assert independent reproduction. ### CE Accuracy: 32.31. Result ID: 6a3a5c6dfbc373592c369399. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"MobileNetL"}. This record does not assert independent reproduction. ### MM Accuracy: 26.17. Result ID: 6a3a5c6dfbc373592c36939c. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"MobileNetL"}. This record does not assert independent reproduction. ### DICE Accuracy: 15.35. Result ID: 6a3a5c6dfbc373592c3693a5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"PARN18"}. This record does not assert independent reproduction. ### DICE Accuracy: 2.03. Result ID: 6a3a5c6dfbc373592c36939b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"MobileNetL"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.