# Image Classification on Aircraft (Metrics: Error %, ECE, NLL) Source: [Image Classification on Aircraft (Metrics: Error %, ECE, NLL)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:42:19.517Z Evaluation of Image Classification performance on the Aircraft dataset, reporting Error rate, Expected Calibration Error (ECE), and Negative Log-Likelihood (NLL). 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) | Aircraft | | Metric | Error Rate | | Unit | PERCENT | | Direction | Lower is better | | Results loaded | 12 of 12 | | 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 - [Error Rate](): Lower is better; unit: PERCENT. - [Expected Calibration Error](): Lower is better; unit: SCALAR. - [Negative Log-Likelihood](): Lower is better; unit: SCALAR. ## Recorded results | Method | Error Rate | Result date | Report paper | | --- | --- | --- | --- | | Ours | 44.196 | Not recorded | 698575d7c97a0b3e3b5d5e86 | | ADVI | 45.42 | Not recorded | 698575d7c97a0b3e3b5d5e86 | | MC-Dropout | 45.97 | Not recorded | 698575d7c97a0b3e3b5d5e86 | | Lap. Approx. | 46.0425 | Not recorded | 698575d7c97a0b3e3b5d5e86 | | SGLD | 47.514 | Not recorded | 698575d7c97a0b3e3b5d5e86 | | Vanilla | 48.01 | Not recorded | 698575d7c97a0b3e3b5d5e86 | | Ours | 52.318 | Not recorded | 698575d7c97a0b3e3b5d5e86 | | SGLD | 52.9125 | Not recorded | 698575d7c97a0b3e3b5d5e86 | | ADVI | 53.002 | Not recorded | 698575d7c97a0b3e3b5d5e86 | | MC-Dropout | 53.2133 | Not recorded | 698575d7c97a0b3e3b5d5e86 | | Lap. Approx. | 53.56 | Not recorded | 698575d7c97a0b3e3b5d5e86 | | Vanilla | 54.3 | Not recorded | 698575d7c97a0b3e3b5d5e86 | ### Ours Error Rate: 44.196. Result ID: 6998ee265698665ec452ba87. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet101"}. This record does not assert independent reproduction. ### ADVI Error Rate: 45.42. Result ID: 6998ee265698665ec452ba7f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet101"}. This record does not assert independent reproduction. ### MC-Dropout Error Rate: 45.97. Result ID: 6998ee265698665ec452ba81. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet101"}. This record does not assert independent reproduction. ### Lap. Approx. Error Rate: 46.0425. Result ID: 6998ee265698665ec452ba85. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet101"}. This record does not assert independent reproduction. ### SGLD Error Rate: 47.514. Result ID: 6998ee265698665ec452ba83. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet101"}. This record does not assert independent reproduction. ### Vanilla Error Rate: 48.01. Result ID: 6998ee265698665ec452ba7d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet101"}. This record does not assert independent reproduction. ### Ours Error Rate: 52.318. Result ID: 6998ee265698665ec452ba88. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-L-32"}. This record does not assert independent reproduction. ### SGLD Error Rate: 52.9125. Result ID: 6998ee265698665ec452ba84. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT-L-32"}. This record does not assert independent reproduction. ### ADVI Error Rate: 53.002. Result ID: 6998ee265698665ec452ba80. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-L-32"}. This record does not assert independent reproduction. ### MC-Dropout Error Rate: 53.2133. Result ID: 6998ee265698665ec452ba82. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-L-32"}. This record does not assert independent reproduction. ### Lap. Approx. Error Rate: 53.56. Result ID: 6998ee265698665ec452ba86. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-L-32"}. This record does not assert independent reproduction. ### Vanilla Error Rate: 54.3. Result ID: 6998ee265698665ec452ba7e. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT-L-32"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.