# Image Classification on CIFAR80N (test) Source: [Image Classification on CIFAR80N (test)]() Collection index: [llms.txt]() Data updated: 2026-03-19T08:17:07.543Z Evaluation of Image Classification performance on the CIFAR80N test set, reporting accuracy under various uniform noise levels (20%, 50%, 80%) and flip noise (40%). 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) | CIFAR80N (test) | | Metric | Accuracy (Uniform 20% Noise) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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 (Uniform 20% Noise)](): Higher is better; unit: PERCENT. - [Accuracy (Uniform 50% Noise)](): Higher is better; unit: PERCENT. - [Accuracy (Uniform 80% Noise)](): Higher is better; unit: PERCENT. - [Accuracy (Flip 40% Noise)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Uniform 20% Noise) | Result date | Report paper | | --- | --- | --- | --- | | VRI | 72.9 | Not recorded | 69bb82f50636e5bf4afc1957 | | USDNL | 71.54 | Not recorded | 69bb82f50636e5bf4afc1957 | | PNP-soft | 67 | Not recorded | 69bb82f50636e5bf4afc1957 | | PNP-hard | 65.87 | Not recorded | 69bb82f50636e5bf4afc1957 | | Jo-SRC | 65.83 | Not recorded | 69bb82f50636e5bf4afc1957 | | MoPro | 65.6 | Not recorded | 69bb82f50636e5bf4afc1957 | | Co-teaching | 60.38 | Not recorded | 69bb82f50636e5bf4afc1957 | | JoCoR | 59.99 | Not recorded | 69bb82f50636e5bf4afc1957 | | Co-teaching+ | 53.97 | Not recorded | 69bb82f50636e5bf4afc1957 | | Decoupling | 43.49 | Not recorded | 69bb82f50636e5bf4afc1957 | | Cross-Entropy | 42.57 | Not recorded | 69bb82f50636e5bf4afc1957 | ### VRI Accuracy (Uniform 20% Noise): 72.9. Result ID: 69bbb0e547f34ce924a572ee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation protocol":"average over the last 10 epochs"}. This record does not assert independent reproduction. ### USDNL Accuracy (Uniform 20% Noise): 71.54. Result ID: 69bbb0e547f34ce924a572ed. [Reporting paper]() Recorded evaluation configuration: {"Evaluation protocol":"average over the last 10 epochs"}. This record does not assert independent reproduction. ### PNP-soft Accuracy (Uniform 20% Noise): 67. Result ID: 69bbb0e547f34ce924a572ec. [Reporting paper]() Recorded evaluation configuration: {"Evaluation protocol":"average over the last 10 epochs"}. This record does not assert independent reproduction. ### PNP-hard Accuracy (Uniform 20% Noise): 65.87. Result ID: 69bbb0e547f34ce924a572eb. [Reporting paper]() Recorded evaluation configuration: {"Evaluation protocol":"average over the last 10 epochs"}. This record does not assert independent reproduction. ### Jo-SRC Accuracy (Uniform 20% Noise): 65.83. Result ID: 69bbb0e547f34ce924a572ea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation protocol":"average over the last 10 epochs"}. This record does not assert independent reproduction. ### MoPro Accuracy (Uniform 20% Noise): 65.6. Result ID: 69bbb0e547f34ce924a572e9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation protocol":"average over the last 10 epochs"}. This record does not assert independent reproduction. ### Co-teaching Accuracy (Uniform 20% Noise): 60.38. Result ID: 69bbb0e547f34ce924a572e6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation protocol":"average over the last 10 epochs"}. This record does not assert independent reproduction. ### JoCoR Accuracy (Uniform 20% Noise): 59.99. Result ID: 69bbb0e547f34ce924a572e8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation protocol":"average over the last 10 epochs"}. This record does not assert independent reproduction. ### Co-teaching+ Accuracy (Uniform 20% Noise): 53.97. Result ID: 69bbb0e547f34ce924a572e7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation protocol":"average over the last 10 epochs"}. This record does not assert independent reproduction. ### Decoupling Accuracy (Uniform 20% Noise): 43.49. Result ID: 69bbb0e547f34ce924a572e5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation protocol":"average over the last 10 epochs"}. This record does not assert independent reproduction. ### Cross-Entropy Accuracy (Uniform 20% Noise): 42.57. Result ID: 69bbb0e547f34ce924a572e4. [Reporting paper]() Recorded evaluation configuration: {"Evaluation protocol":"average over the last 10 epochs"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.