# Classification on CIFAR-10 20% IDN (test) Source: [Classification on CIFAR-10 20% IDN (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:28:20.681Z Evaluation of Classification performance on a 20% subset of the CIFAR-10 test set, sampled using an IDN (Independent and Identically Distributed) methodology. 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 | Classification | | Dataset (including any stated split) | CIFAR-10 20% IDN (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 28 of 28 | | 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 | | --- | --- | --- | --- | | kMEIDTM | 92.26 | Not recorded | 68fa6cb41e209131cea355df | | MEIDTM | 91.38 | Not recorded | 68fa6cb41e209131cea355df | | DMI | 89.99 | Not recorded | 68fa6cb41e209131cea355df | | CoTeaching++ | 89.78 | Not recorded | 68fa6cb41e209131cea355df | | Forward | 89.62 | Not recorded | 68fa6cb41e209131cea355df | | PartT | 89.33 | Not recorded | 68fa6cb41e209131cea355df | | JoCor | 89.3 | Not recorded | 68fa6cb41e209131cea355df | | TMDNN | 89.21 | Not recorded | 68fa6cb41e209131cea355df | | GCE | 88.89 | Not recorded | 68fa6cb41e209131cea355df | | CoTeaching | 88.43 | Not recorded | 68fa6cb41e209131cea355df | | PeerLoss | 88.14 | Not recorded | 68fa6cb41e209131cea355df | | SEAL | 87.79 | Not recorded | 68fa68dd1e209131cea1ec83 | | Co-teaching | 87.28 | Not recorded | 68fa68dd1e209131cea1ec83 | | CE (baseline) | 86.93 | Not recorded | 68fa6cb41e209131cea355df | | DMI | 86.57 | Not recorded | 68fa68dd1e209131cea1ec83 | | GCE | 86.44 | Not recorded | 68fa68dd1e209131cea1ec83 | | Forward | 86.35 | Not recorded | 68fa68dd1e209131cea1ec83 | | CE | 86.34 | Not recorded | 68fa68dd1e209131cea1ec83 | | DAC | 86.16 | Not recorded | 68fa68dd1e209131cea1ec83 | | CausalNL | 81.47 | Not recorded | 68fa6cb81e209131cea35949 | | MentorNet | 81.03 | Not recorded | 68fa6cb81e209131cea35949 | | Co-teaching | 80.96 | Not recorded | 68fa6cb81e209131cea35949 | | Decoupling | 78.71 | Not recorded | 68fa6cb81e209131cea35949 | | Reweight | 76.23 | Not recorded | 68fa6cb81e209131cea35949 | | T-Revision | 76.15 | Not recorded | 68fa6cb81e209131cea35949 | | CE | 75.81 | Not recorded | 68fa6cb81e209131cea35949 | | Forward | 74.64 | Not recorded | 68fa6cb81e209131cea35949 | | Mixup | 73.17 | Not recorded | 68fa6cb81e209131cea35949 | ### kMEIDTM Accuracy: 92.26. Result ID: 698f30623a6c314849f6d49b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MEIDTM Accuracy: 91.38. Result ID: 698f30623a6c314849f6d49a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DMI Accuracy: 89.99. Result ID: 698f30623a6c314849f6d492. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CoTeaching++ Accuracy: 89.78. Result ID: 698f30623a6c314849f6d495. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Forward Accuracy: 89.62. Result ID: 698f30623a6c314849f6d493. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### PartT Accuracy: 89.33. Result ID: 698f30623a6c314849f6d499. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### JoCor Accuracy: 89.3. Result ID: 698f30623a6c314849f6d496. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### TMDNN Accuracy: 89.21. Result ID: 698f30623a6c314849f6d498. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GCE Accuracy: 88.89. Result ID: 698f30623a6c314849f6d491. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CoTeaching Accuracy: 88.43. Result ID: 698f30623a6c314849f6d494. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### PeerLoss Accuracy: 88.14. Result ID: 698f30623a6c314849f6d497. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SEAL Accuracy: 87.79. Result ID: 698d8ada8b517eb43322404b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Noise Fraction":"20%"}. This record does not assert independent reproduction. ### Co-teaching Accuracy: 87.28. Result ID: 698d8ada8b517eb433224047. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Noise Fraction":"20%"}. This record does not assert independent reproduction. ### CE (baseline) Accuracy: 86.93. Result ID: 698f30623a6c314849f6d490. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DMI Accuracy: 86.57. Result ID: 698d8ada8b517eb43322404a. [Reporting paper]() Recorded evaluation configuration: {"Noise Fraction":"20%"}. This record does not assert independent reproduction. ### GCE Accuracy: 86.44. Result ID: 698d8ada8b517eb433224048. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Noise Fraction":"20%"}. This record does not assert independent reproduction. ### Forward Accuracy: 86.35. Result ID: 698d8ada8b517eb433224046. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Noise Fraction":"20%"}. This record does not assert independent reproduction. ### CE Accuracy: 86.34. Result ID: 698d8ada8b517eb433224045. [Reporting paper]() Recorded evaluation configuration: {"Noise Fraction":"20%"}. This record does not assert independent reproduction. ### DAC Accuracy: 86.16. Result ID: 698d8ada8b517eb433224049. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Noise Fraction":"20%"}. This record does not assert independent reproduction. ### CausalNL Accuracy: 81.47. Result ID: 698f36373a6c314849f70d2a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MentorNet Accuracy: 81.03. Result ID: 698f36373a6c314849f70d25. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Co-teaching Accuracy: 80.96. Result ID: 698f36373a6c314849f70d23. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Decoupling Accuracy: 78.71. Result ID: 698f36373a6c314849f70d24. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Reweight Accuracy: 76.23. Result ID: 698f36373a6c314849f70d28. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### T-Revision Accuracy: 76.15. Result ID: 698f36373a6c314849f70d29. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CE Accuracy: 75.81. Result ID: 698f36373a6c314849f70d22. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Forward Accuracy: 74.64. Result ID: 698f36373a6c314849f70d27. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Mixup Accuracy: 73.17. Result ID: 698f36373a6c314849f70d26. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.