# Image Classification on CIFAR-10 (test) (Calibration Metrics) Source: [Image Classification on CIFAR-10 (test) (Calibration Metrics)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:41:21.599Z Evaluation of Image Classification model calibration performance on the CIFAR-10 test set, specifically reporting Expected Calibration Error (ECE) and Adaptive Expected Calibration Error (AECE). 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) | CIFAR 10 (test) | | Metric | ECE | | Unit | PERCENT | | Direction | Lower is better | | Results loaded | 14 of 14 | | 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 - [ECE](): Lower is better; unit: PERCENT. - [AECE](): Lower is better; unit: PERCENT. ## Recorded results | Method | ECE | Result date | Report paper | | --- | --- | --- | --- | | MbLS | 1.16 | Not recorded | 68fa6ff81e209131cea483d7 | | MbLS | 1.38 | Not recorded | 68fa6ff81e209131cea483d7 | | LS | 2.79 | Not recorded | 68fa6ff81e209131cea483d7 | | ECP | 3.01 | Not recorded | 68fa6ff81e209131cea483d7 | | MbLS (m=0) | 3.07 | Not recorded | 68fa6ff81e209131cea483d7 | | LS | 3.56 | Not recorded | 68fa6ff81e209131cea483d7 | | MbLS (m=0) | 3.72 | Not recorded | 68fa6ff81e209131cea483d7 | | FLSD | 3.84 | Not recorded | 68fa6ff81e209131cea483d7 | | FL | 3.9 | Not recorded | 68fa6ff81e209131cea483d7 | | FLSD | 4.58 | Not recorded | 68fa6ff81e209131cea483d7 | | FL | 4.6 | Not recorded | 68fa6ff81e209131cea483d7 | | ECP | 5.41 | Not recorded | 68fa6ff81e209131cea483d7 | | CE | 5.74 | Not recorded | 68fa6ff81e209131cea483d7 | | CE | 5.85 | Not recorded | 68fa6ff81e209131cea483d7 | ### MbLS ECE: 1.16. Result ID: 6990f2f63a6c3148490486ca. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### MbLS ECE: 1.38. Result ID: 6990f2f63a6c3148490486cb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-101"}. This record does not assert independent reproduction. ### LS ECE: 2.79. Result ID: 6990f2f63a6c3148490486c2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### ECP ECE: 3.01. Result ID: 6990f2f63a6c3148490486c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### MbLS (m=0) ECE: 3.07. Result ID: 6990f2f63a6c3148490486c9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-101","margin":0}. This record does not assert independent reproduction. ### LS ECE: 3.56. Result ID: 6990f2f63a6c3148490486c3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-101"}. This record does not assert independent reproduction. ### MbLS (m=0) ECE: 3.72. Result ID: 6990f2f63a6c3148490486c8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","margin":0}. This record does not assert independent reproduction. ### FLSD ECE: 3.84. Result ID: 6990f2f63a6c3148490486c6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### FL ECE: 3.9. Result ID: 6990f2f63a6c3148490486c4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. ### FLSD ECE: 4.58. Result ID: 6990f2f63a6c3148490486c7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-101"}. This record does not assert independent reproduction. ### FL ECE: 4.6. Result ID: 6990f2f63a6c3148490486c5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-101"}. This record does not assert independent reproduction. ### ECP ECE: 5.41. Result ID: 6990f2f63a6c3148490486c1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-101"}. This record does not assert independent reproduction. ### CE ECE: 5.74. Result ID: 6990f2f63a6c3148490486bf. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet-101"}. This record does not assert independent reproduction. ### CE ECE: 5.85. Result ID: 6990f2f63a6c3148490486be. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.