# Image Classification on Imagenette (Robust Accuracy Metrics) Source: [Image Classification on Imagenette (Robust Accuracy Metrics)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:39:19.161Z Evaluation of Image Classification performance on the Imagenette dataset, focusing on adversarial robustness measured by Clean Accuracy and Robust Accuracy at specific epsilon values (eps=2/255 and eps=4/255). 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) | Imagenette | | Metric | Clean Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 5 of 5 | | 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 - [Clean Accuracy](): Higher is better; unit: PERCENT. - [Robust Accuracy (eps=2/255)](): Higher is better; unit: PERCENT. - [Robust Accuracy (eps=4/255)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Clean Accuracy | Result date | Report paper | | --- | --- | --- | --- | | FuseLIP | 93.6 | Not recorded | 699bdef109c33900fcd8041f | | FuseLIP | 91.8 | Not recorded | 699bdef109c33900fcd8041f | | FuseLIP | 89.6 | Not recorded | 699bdef109c33900fcd8041f | | FuseLIP | 87 | Not recorded | 699bdef109c33900fcd8041f | | FuseLIP | 83.4 | Not recorded | 699bdef109c33900fcd8041f | ### FuseLIP Clean Accuracy: 93.6. Result ID: 699d09a65698665ec4a9ad93. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tokenizer":"clean","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### FuseLIP Clean Accuracy: 91.8. Result ID: 699d09a65698665ec4a9ad94. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tokenizer":"AT 4/255","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### FuseLIP Clean Accuracy: 89.6. Result ID: 699d09a65698665ec4a9ad95. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tokenizer":"AT 8/255","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### FuseLIP Clean Accuracy: 87. Result ID: 699d09a65698665ec4a9ad96. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tokenizer":"AT 12/255","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### FuseLIP Clean Accuracy: 83.4. Result ID: 699d09a65698665ec4a9ad97. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Tokenizer":"AT 16/255","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.