# Image Classification on ImageNet-9 Mixed-Next v1 (test) Source: [Image Classification on ImageNet-9 Mixed-Next v1 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:27:54.684Z Evaluation of Image Classification performance on the test split of the ImageNet-9 Mixed-Next v1 dataset, measured using 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) | ImageNet-9 Mixed-Next v1 (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 | | --- | --- | --- | --- | | CF + F + Saliency Combination | 55.5 | Not recorded | 68fa6a0b1e209131cea25b44 | | CF + F Combination | 54.2 | Not recorded | 68fa6a0b1e209131cea25b44 | | Factual Augmentation (F) | 53.3 | Not recorded | 68fa6a0b1e209131cea25b44 | | Factual Augmentation (F) | 53 | Not recorded | 68fa6a0b1e209131cea25b44 | | F + Saliency Combination | 52.8 | Not recorded | 68fa6a0b1e209131cea25b44 | | Counterfactual Augmentation (CF) | 50 | Not recorded | 68fa6a0b1e209131cea25b44 | | CF + Saliency Combination | 49.9 | Not recorded | 68fa6a0b1e209131cea25b44 | | Counterfactual Augmentation (CF) | 49.3 | Not recorded | 68fa6a0b1e209131cea25b44 | | Counterfactual Augmentation (CF) | 48.8 | Not recorded | 68fa6a0b1e209131cea25b44 | | Saliency regularization (Sal) | 48.5 | Not recorded | 68fa6a0b1e209131cea25b44 | | Label Smoothing (LS) | 48.5 | Not recorded | 68fa6a0b1e209131cea25b44 | | Counterfactual Augmentation (CF) | 48.4 | Not recorded | 68fa6a0b1e209131cea25b44 | | Mixup | 48.2 | Not recorded | 68fa6a0b1e209131cea25b44 | | Factual Augmentation (F) | 47.9 | Not recorded | 68fa6a0b1e209131cea25b44 | | Original Baseline | 47.5 | Not recorded | 68fa6a0b1e209131cea25b44 | | Counterfactual Augmentation (CF) | 45.9 | Not recorded | 68fa6a0b1e209131cea25b44 | ### CF + F + Saliency Combination Accuracy: 55.5. Result ID: 698e03a2ffc3901de09a27a3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"CF variant":"CAGAN","F variant":"Shuffle","Saliency regularization":true}. This record does not assert independent reproduction. ### CF + F Combination Accuracy: 54.2. Result ID: 698e03a2ffc3901de09a27a0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"CF variant":"CAGAN","F variant":"Shuffle"}. This record does not assert independent reproduction. ### Factual Augmentation (F) Accuracy: 53.3. Result ID: 698e03a2ffc3901de09a279e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Variant":"Shuffle"}. This record does not assert independent reproduction. ### Factual Augmentation (F) Accuracy: 53. Result ID: 698e03a2ffc3901de09a279d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Variant":"Random"}. This record does not assert independent reproduction. ### F + Saliency Combination Accuracy: 52.8. Result ID: 698e03a2ffc3901de09a27a2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"F variant":"Shuffle","Saliency regularization":true}. This record does not assert independent reproduction. ### Counterfactual Augmentation (CF) Accuracy: 50. Result ID: 698e03a2ffc3901de09a279c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Variant":"CAGAN"}. This record does not assert independent reproduction. ### CF + Saliency Combination Accuracy: 49.9. Result ID: 698e03a2ffc3901de09a27a1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"CF variant":"CAGAN","Saliency regularization":true}. This record does not assert independent reproduction. ### Counterfactual Augmentation (CF) Accuracy: 49.3. Result ID: 698e03a2ffc3901de09a2799. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Variant":"Random"}. This record does not assert independent reproduction. ### Counterfactual Augmentation (CF) Accuracy: 48.8. Result ID: 698e03a2ffc3901de09a2798. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Variant":"Grey"}. This record does not assert independent reproduction. ### Saliency regularization (Sal) Accuracy: 48.5. Result ID: 698e03a2ffc3901de09a2797. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"lambda":"10^-4"}. This record does not assert independent reproduction. ### Label Smoothing (LS) Accuracy: 48.5. Result ID: 698e03a2ffc3901de09a27a5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":0.1}. This record does not assert independent reproduction. ### Counterfactual Augmentation (CF) Accuracy: 48.4. Result ID: 698e03a2ffc3901de09a279a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Variant":"Shuffle"}. This record does not assert independent reproduction. ### Mixup Accuracy: 48.2. Result ID: 698e03a2ffc3901de09a27a4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"alpha":0.2}. This record does not assert independent reproduction. ### Factual Augmentation (F) Accuracy: 47.9. Result ID: 698e03a2ffc3901de09a279f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Variant":"FGSM","epsilon":0.5}. This record does not assert independent reproduction. ### Original Baseline Accuracy: 47.5. Result ID: 698e03a2ffc3901de09a2796. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Counterfactual Augmentation (CF) Accuracy: 45.9. Result ID: 698e03a2ffc3901de09a279b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Variant":"Tile"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.