# Image Classification on FMNIST (ACC, NLL, ECE) Source: [Image Classification on FMNIST (ACC, NLL, ECE)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:32:56.709Z Evaluation of Image Classification performance and model calibration on the Fashion MNIST dataset, reporting Accuracy (ACC), Negative Log-Likelihood (NLL), and Expected Calibration Error (ECE). 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) | FMNIST | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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. - [NLL](): Lower is better; unit: SCALAR. - [ECE](): Lower is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | VaLLA | 86.7 | Not recorded | 6993f6ab9ebc499c97409fe7 | | VaLLA | 86.5 | Not recorded | 6993f6ab9ebc499c97409fe7 | | MAP | 85.9 | Not recorded | 6993f6ab9ebc499c97409fe7 | | LLA | 85.9 | Not recorded | 6993f6ab9ebc499c97409fe7 | | LLA | 85.9 | Not recorded | 6993f6ab9ebc499c97409fe7 | | ELLA | 85.9 | Not recorded | 6993f6ab9ebc499c97409fe7 | | GAPA | 85.9 | Not recorded | 6993f6ab9ebc499c97409fe7 | | LLA | 85.8 | Not recorded | 6993f6ab9ebc499c97409fe7 | | Linear Probing | 85.8 | Not recorded | 6993f6ab9ebc499c97409fe7 | | Dropout | 85.8 | Not recorded | 6993f6ab9ebc499c97409fe7 | | GPP | 85.7 | Not recorded | 6993f6ab9ebc499c97409fe7 | | LLA | 85.6 | Not recorded | 6993f6ab9ebc499c97409fe7 | | Ensemble | 83.9 | Not recorded | 6993f6ab9ebc499c97409fe7 | ### VaLLA Accuracy: 86.7. Result ID: 699a9dcf5698665ec4298cd4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Inducing points":200}. This record does not assert independent reproduction. ### VaLLA Accuracy: 86.5. Result ID: 699a9dcf5698665ec4298cd3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Inducing points":100}. This record does not assert independent reproduction. ### MAP Accuracy: 85.9. Result ID: 699a9dcf5698665ec4298ccd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LLA Accuracy: 85.9. Result ID: 699a9dcf5698665ec4298cd0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"last-layer"}. This record does not assert independent reproduction. ### LLA Accuracy: 85.9. Result ID: 699a9dcf5698665ec4298cd1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"last-layer","Approximation":"KFAC"}. This record does not assert independent reproduction. ### ELLA Accuracy: 85.9. Result ID: 699a9dcf5698665ec4298cd2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GAPA Accuracy: 85.9. Result ID: 699a9dcf5698665ec4298cd9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LLA Accuracy: 85.8. Result ID: 699a9dcf5698665ec4298ccf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Approximation":"KFAC"}. This record does not assert independent reproduction. ### Linear Probing Accuracy: 85.8. Result ID: 699a9dcf5698665ec4298cd5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Dropout Accuracy: 85.8. Result ID: 699a9dcf5698665ec4298cd7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPP Accuracy: 85.7. Result ID: 699a9dcf5698665ec4298cd6. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LLA Accuracy: 85.6. Result ID: 699a9dcf5698665ec4298cce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Approximation":"Diagonal"}. This record does not assert independent reproduction. ### Ensemble Accuracy: 83.9. Result ID: 699a9dcf5698665ec4298cd8. [Reporting paper]() [Method origin paper]() 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.