# Image Classification on CIFAR-10 (test) (IR-NR Robustness Error Rates) Source: [Image Classification on CIFAR-10 (test) (IR-NR Robustness Error Rates)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:07:19.684Z Evaluation of Image Classification performance on the CIFAR-10 test set, specifically reporting top-1 error rates under various IR-NR perturbation conditions. 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 (test) | | Metric | Top-1 Error Rate (IR-NR 1-0.0) | | Unit | PERCENT | | Direction | Lower is better | | Results loaded | 8 of 8 | | 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 - [Top-1 Error Rate (IR-NR 1-0.0)](): Lower is better; unit: PERCENT. - [Top-1 Error Rate (IR-NR 10-0.0)](): Lower is better; unit: PERCENT. - [Top-1 Error Rate (IR-NR 1-0.1)](): Lower is better; unit: PERCENT. - [Top-1 Error Rate (IR-NR 10-0.1)](): Lower is better; unit: PERCENT. ## Recorded results | Method | Top-1 Error Rate (IR-NR 1-0.0) | Result date | Report paper | | --- | --- | --- | --- | | lambda\_A,W,S (AutoDO) | 4.9 | Not recorded | 68fa69801e209131cea2284e | | FAA | 5 | Not recorded | 68fa69801e209131cea2284e | | RAA | 5.2 | Not recorded | 68fa69801e209131cea2284e | | lambda\_A (AutoDO) | 5.2 | Not recorded | 68fa69801e209131cea2284e | | lambda\_A,W (AutoDO) | 5.4 | Not recorded | 68fa69801e209131cea2284e | | DADA | 5.5 | Not recorded | 68fa69801e209131cea2284e | | lambda\_ASHA (AutoDO) | 5.9 | Not recorded | 68fa69801e209131cea2284e | | Baseline | 6 | Not recorded | 68fa69801e209131cea2284e | ### lambda\_A,W,S (AutoDO) Top-1 Error Rate (IR-NR 1-0.0): 4.9. Result ID: 698db2a58b517eb433232e6f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Wide-ResNet-28-10","Configuration":"per-point augmentation, loss reweighting, and soft-labeling"}. This record does not assert independent reproduction. ### FAA Top-1 Error Rate (IR-NR 1-0.0): 5. Result ID: 698db2a58b517eb433232e6a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Wide-ResNet-28-10"}. This record does not assert independent reproduction. ### RAA Top-1 Error Rate (IR-NR 1-0.0): 5.2. Result ID: 698db2a58b517eb433232e69. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Wide-ResNet-28-10"}. This record does not assert independent reproduction. ### lambda\_A (AutoDO) Top-1 Error Rate (IR-NR 1-0.0): 5.2. Result ID: 698db2a58b517eb433232e6d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Wide-ResNet-28-10","Configuration":"per-point augmentation hyperparameters"}. This record does not assert independent reproduction. ### lambda\_A,W (AutoDO) Top-1 Error Rate (IR-NR 1-0.0): 5.4. Result ID: 698db2a58b517eb433232e6e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Wide-ResNet-28-10","Configuration":"per-point augmentation and loss reweighting"}. This record does not assert independent reproduction. ### DADA Top-1 Error Rate (IR-NR 1-0.0): 5.5. Result ID: 698db2a58b517eb433232e6b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Wide-ResNet-28-10"}. This record does not assert independent reproduction. ### lambda\_ASHA (AutoDO) Top-1 Error Rate (IR-NR 1-0.0): 5.9. Result ID: 698db2a58b517eb433232e6c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Wide-ResNet-28-10","Configuration":"shared augmentation hyperparameters"}. This record does not assert independent reproduction. ### Baseline Top-1 Error Rate (IR-NR 1-0.0): 6. Result ID: 698db2a58b517eb433232e68. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Wide-ResNet-28-10","Augmentation":"Standard (cropping, flipping, erasing)"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.