# Image Classification on CIFAR-10-C CS-3 1.0 (test) Source: [Image Classification on CIFAR-10-C CS-3 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:51:50.821Z Evaluation of Image Classification performance on the specific CIFAR-10-C corruption set variant (CS-3 1.0) test split, measured by Mean Accuracy. 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) | CIFAR-10-C CS-3 1.0 (test) | | Metric | Mean Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [Mean Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Mean Accuracy | Result date | Report paper | | --- | --- | --- | --- | | DynACL-AIR | 74.31 | Not recorded | 68fa70f21e209131cea4e438 | | ACL-AIR | 73.33 | Not recorded | 68fa70f21e209131cea4e438 | | ACL-AIR | 72.95 | Not recorded | 68fa70f21e209131cea4e438 | | DynACL | 72.95 | Not recorded | 68fa70f21e209131cea4e438 | | ACL | 72.54 | Not recorded | 68fa70f21e209131cea4e438 | | ACL | 71.78 | Not recorded | 68fa70f21e209131cea4e438 | | ACL-AIR | 71.38 | Not recorded | 68fa70f21e209131cea4e438 | | DynACL-AIR | 70.16 | Not recorded | 68fa70f21e209131cea4e438 | | DynACL-AIR | 69.55 | Not recorded | 68fa70f21e209131cea4e438 | | ACL | 69.49 | Not recorded | 68fa70f21e209131cea4e438 | | DynACL | 69.01 | Not recorded | 68fa70f21e209131cea4e438 | | DynACL | 66.95 | Not recorded | 68fa70f21e209131cea4e438 | ### DynACL-AIR Mean Accuracy: 74.31. Result ID: 699181c93a6c314849089d3b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training":"DynACL-AIR","Finetuning procedure":"AFF","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### ACL-AIR Mean Accuracy: 73.33. Result ID: 699181c93a6c314849089d31. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training":"ACL-AIR","Finetuning procedure":"SLF","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### ACL-AIR Mean Accuracy: 72.95. Result ID: 699181c93a6c314849089d39. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training":"ACL-AIR","Finetuning procedure":"AFF","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### DynACL Mean Accuracy: 72.95. Result ID: 699181c93a6c314849089d3a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training":"DynACL","Finetuning procedure":"AFF","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### ACL Mean Accuracy: 72.54. Result ID: 699181c93a6c314849089d38. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training":"ACL","Finetuning procedure":"AFF","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### ACL Mean Accuracy: 71.78. Result ID: 699181c93a6c314849089d30. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training":"ACL","Finetuning procedure":"SLF","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### ACL-AIR Mean Accuracy: 71.38. Result ID: 699181c93a6c314849089d35. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training":"ACL-AIR","Finetuning procedure":"ALF","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### DynACL-AIR Mean Accuracy: 70.16. Result ID: 699181c93a6c314849089d33. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training":"DynACL-AIR","Finetuning procedure":"SLF","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### DynACL-AIR Mean Accuracy: 69.55. Result ID: 699181c93a6c314849089d37. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training":"DynACL-AIR","Finetuning procedure":"ALF","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### ACL Mean Accuracy: 69.49. Result ID: 699181c93a6c314849089d34. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training":"ACL","Finetuning procedure":"ALF","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### DynACL Mean Accuracy: 69.01. Result ID: 699181c93a6c314849089d32. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training":"DynACL","Finetuning procedure":"SLF","Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### DynACL Mean Accuracy: 66.95. Result ID: 699181c93a6c314849089d36. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training":"DynACL","Finetuning procedure":"ALF","Backbone":"ResNet-18"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.