# Resolving Confusion (RC) on CIFAR-5 Source: [Resolving Confusion (RC) on CIFAR-5]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:06:16.757Z Evaluation of model performance on the CIFAR-5 dataset specifically measuring test error, retention error, and forgetting error related to confusion resolution, including incremental learning (IC) and forgetting (Fgt) variants. 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 | Resolving Confusion (RC) | | Dataset (including any stated split) | CIFAR-5 | | Metric | Test Error (mean) | | Unit | PERCENT | | Direction | Lower is better | | Results loaded | 19 of 19 | | 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 - [Test Error (mean)](): Lower is better; unit: PERCENT. - [Test Error (std)](): Lower is better; unit: PERCENT. - [Retain Error (mean)](): Lower is better; unit: PERCENT. - [Retain Error (std)](): Lower is better; unit: PERCENT. - [Forget Error (mean)](): Lower is better; unit: PERCENT. - [Forget Error (std)](): Lower is better; unit: PERCENT. - [IC Test Error (mean)](): Lower is better; unit: PERCENT. - [IC Test Error (std)](): Lower is better; unit: PERCENT. - [IC Retain Error (mean)](): Lower is better; unit: PERCENT. - [IC Retain Error (std)](): Lower is better; unit: PERCENT. - [Fgt Test Error (mean)](): Lower is better; unit: PERCENT. - [Fgt Test Error (std)](): Lower is better; unit: PERCENT. - [Fgt Retain Error (mean)](): Lower is better; unit: PERCENT. - [Fgt Retain Error (std)](): Lower is better; unit: PERCENT. ## Recorded results | Method | Test Error (mean) | Result date | Report paper | | --- | --- | --- | --- | | CF-k | 22.6 | Not recorded | 68fa71011e209131cea4e7b9 | | EU-k | 23.5 | Not recorded | 68fa71011e209131cea4e7b9 | | Original | 24.2 | Not recorded | 68fa71011e209131cea4e7b9 | | SCRUB | 24.2 | Not recorded | 68fa71011e209131cea4e7b9 | | Finetune | 24.3 | Not recorded | 68fa71011e209131cea4e7b9 | | Retrain | 24.4 | Not recorded | 68fa71011e209131cea4e7b9 | | NTK | 24.4 | Not recorded | 68fa71011e209131cea4e7b9 | | Retrain | 24.9 | Not recorded | 68fa71011e209131cea4e7b9 | | SCRUB | 25 | Not recorded | 68fa71011e209131cea4e7b9 | | NegGrad+ | 25.5 | Not recorded | 68fa71011e209131cea4e7b9 | | Bad-T | 27.73 | Not recorded | 68fa71011e209131cea4e7b9 | | Fisher | 31.6 | Not recorded | 68fa71011e209131cea4e7b9 | | NTK | 32.2 | Not recorded | 68fa71011e209131cea4e7b9 | | NegGrad+ | 33.53 | Not recorded | 68fa71011e209131cea4e7b9 | | Finetune | 34.33 | Not recorded | 68fa71011e209131cea4e7b9 | | CF-k | 36.13 | Not recorded | 68fa71011e209131cea4e7b9 | | Original | 37.07 | Not recorded | 68fa71011e209131cea4e7b9 | | EU-k | 51.6 | Not recorded | 68fa71011e209131cea4e7b9 | | Fisher | 51.93 | Not recorded | 68fa71011e209131cea4e7b9 | ### CF-k Test Error (mean): 22.6. Result ID: 699186293a6c31484908b6f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet","Scale":"Small-scale"}. This record does not assert independent reproduction. ### EU-k Test Error (mean): 23.5. Result ID: 699186293a6c31484908b6f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet","Scale":"Small-scale"}. This record does not assert independent reproduction. ### Original Test Error (mean): 24.2. Result ID: 699186293a6c31484908b6f1. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet","Scale":"Small-scale"}. This record does not assert independent reproduction. ### SCRUB Test Error (mean): 24.2. Result ID: 699186293a6c31484908b6f9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet","Scale":"Small-scale"}. This record does not assert independent reproduction. ### Finetune Test Error (mean): 24.3. Result ID: 699186293a6c31484908b6f2. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet","Scale":"Small-scale"}. This record does not assert independent reproduction. ### Retrain Test Error (mean): 24.4. Result ID: 699186293a6c31484908b5f5. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"All-CNN","Confused classes":"0, 1","Samples":"50-50"}. This record does not assert independent reproduction. ### NTK Test Error (mean): 24.4. Result ID: 699186293a6c31484908b6f4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet","Scale":"Small-scale"}. This record does not assert independent reproduction. ### Retrain Test Error (mean): 24.9. Result ID: 699186293a6c31484908b6f0. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet","Scale":"Small-scale"}. This record does not assert independent reproduction. ### SCRUB Test Error (mean): 25. Result ID: 699186293a6c31484908b5fd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"All-CNN","Confused classes":"0, 1","Samples":"50-50"}. This record does not assert independent reproduction. ### NegGrad+ Test Error (mean): 25.5. Result ID: 699186293a6c31484908b6f5. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet","Scale":"Small-scale"}. This record does not assert independent reproduction. ### Bad-T Test Error (mean): 27.73. Result ID: 699186293a6c31484908b6f8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet","Scale":"Small-scale"}. This record does not assert independent reproduction. ### Fisher Test Error (mean): 31.6. Result ID: 699186293a6c31484908b6f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet","Scale":"Small-scale"}. This record does not assert independent reproduction. ### NTK Test Error (mean): 32.2. Result ID: 699186293a6c31484908b5fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"All-CNN","Confused classes":"0, 1","Samples":"50-50"}. This record does not assert independent reproduction. ### NegGrad+ Test Error (mean): 33.53. Result ID: 699186293a6c31484908b5f8. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"All-CNN","Confused classes":"0, 1","Samples":"50-50"}. This record does not assert independent reproduction. ### Finetune Test Error (mean): 34.33. Result ID: 699186293a6c31484908b5f7. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"All-CNN","Confused classes":"0, 1","Samples":"50-50"}. This record does not assert independent reproduction. ### CF-k Test Error (mean): 36.13. Result ID: 699186293a6c31484908b5f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"All-CNN","Confused classes":"0, 1","Samples":"50-50"}. This record does not assert independent reproduction. ### Original Test Error (mean): 37.07. Result ID: 699186293a6c31484908b5f6. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"All-CNN","Confused classes":"0, 1","Samples":"50-50"}. This record does not assert independent reproduction. ### EU-k Test Error (mean): 51.6. Result ID: 699186293a6c31484908b5fa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"All-CNN","Confused classes":"0, 1","Samples":"50-50"}. This record does not assert independent reproduction. ### Fisher Test Error (mean): 51.93. Result ID: 699186293a6c31484908b5fb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"All-CNN","Confused classes":"0, 1","Samples":"50-50"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.