# Uncertainty Quantification on FashionMNIST (using V-ID, V-OOD, MI metrics) Source: [Uncertainty Quantification on FashionMNIST (using V-ID, V-OOD, MI metrics)]() Collection index: [llms.txt]() Data updated: 2026-06-01T08:06:05.413Z Evaluation of model uncertainty quantification performance on the FashionMNIST dataset, focusing on variance estimation (V-ID, V-OOD), mutual information (MI-ID, MI-OOD), likelihood prediction (LPPD), and computational overhead (Time, Memory). 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 | Uncertainty Quantification | | Dataset (including any stated split) | FashionMNIST | | Metric | V-ID | | 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 - [V-ID](): Higher is better; unit: PERCENT. - [V-OOD](): Higher is better; unit: PERCENT. - [MI-ID](): Higher is better; unit: PERCENT. - [MI-OOD](): Higher is better; unit: PERCENT. - [LPPD](): Higher is better; unit: SCALAR. - [Time (s)](): Lower is better; unit: TIME. - [Memory (Size)](): Lower is better; unit: SIZE. ## Recorded results | Method | V-ID | Result date | Report paper | | --- | --- | --- | --- | | DE | 92.5 | Not recorded | 6a1d1214dbd7150506f84007 | | DNN-GLM | 92.08 | Not recorded | 6a1d1214dbd7150506f84007 | | SWAG | 91.98 | Not recorded | 6a1d1214dbd7150506f84007 | | LL-GLM | 91.88 | Not recorded | 6a1d1214dbd7150506f84007 | | MC | 91.87 | Not recorded | 6a1d1214dbd7150506f84007 | | LLA | 90.96 | Not recorded | 6a1d1214dbd7150506f84007 | | SMS-UBU | 90.03 | Not recorded | 6a1d1214dbd7150506f84007 | | LL-GLM | 88.05 | Not recorded | 6a1d1214dbd7150506f84007 | | DNN-GLM | 87.91 | Not recorded | 6a1d1214dbd7150506f84007 | | LLA | 87.86 | Not recorded | 6a1d1214dbd7150506f84007 | | DE | 87.51 | Not recorded | 6a1d1214dbd7150506f84007 | | SWAG | 86.84 | Not recorded | 6a1d1214dbd7150506f84007 | | MC | 85.2 | Not recorded | 6a1d1214dbd7150506f84007 | ### DE V-ID: 92.5. Result ID: 6a1d3d5cfbc373592c1642b0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet9"}. This record does not assert independent reproduction. ### DNN-GLM V-ID: 92.08. Result ID: 6a1d3d5cfbc373592c1642ae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet9"}. This record does not assert independent reproduction. ### SWAG V-ID: 91.98. Result ID: 6a1d3d5cfbc373592c1642b2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet9"}. This record does not assert independent reproduction. ### LL-GLM V-ID: 91.88. Result ID: 6a1d3d5cfbc373592c1642af. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet9"}. This record does not assert independent reproduction. ### MC V-ID: 91.87. Result ID: 6a1d3d5cfbc373592c1642b3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet9"}. This record does not assert independent reproduction. ### LLA V-ID: 90.96. Result ID: 6a1d3d5cfbc373592c1642b1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet9"}. This record does not assert independent reproduction. ### SMS-UBU V-ID: 90.03. Result ID: 6a1d3d5cfbc373592c1642b4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet9"}. This record does not assert independent reproduction. ### LL-GLM V-ID: 88.05. Result ID: 6a1d3d5cfbc373592c1642a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LeNet"}. This record does not assert independent reproduction. ### DNN-GLM V-ID: 87.91. Result ID: 6a1d3d5cfbc373592c1642a8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LeNet"}. This record does not assert independent reproduction. ### LLA V-ID: 87.86. Result ID: 6a1d3d5cfbc373592c1642ab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LeNet"}. This record does not assert independent reproduction. ### DE V-ID: 87.51. Result ID: 6a1d3d5cfbc373592c1642aa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LeNet"}. This record does not assert independent reproduction. ### SWAG V-ID: 86.84. Result ID: 6a1d3d5cfbc373592c1642ac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LeNet"}. This record does not assert independent reproduction. ### MC V-ID: 85.2. Result ID: 6a1d3d5cfbc373592c1642ad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LeNet"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.