# Fair Medical Image Classification on HAM10000, Fitzpatrick17K, and CMMD Average Source: [Fair Medical Image Classification on HAM10000, Fitzpatrick17K, and CMMD Average]() Collection index: [llms.txt]() Data updated: 2026-05-29T07:02:34.519Z Average performance evaluation across the HAM10000, Fitzpatrick17K, and CMMD datasets for fair medical image classification, focusing on equity metrics derived from AUC and PSD analysis. 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 | Fair Medical Image Classification | | Dataset (including any stated split) | HAM10000, Fitzpatrick17K, and CMMD Average | | Metric | Avg Overall AUC | | Unit | SCALAR | | Direction | Higher 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 - [Avg Overall AUC](): Higher is better; unit: SCALAR. - [Avg Min AUC](): Higher is better; unit: SCALAR. - [Avg ES-AUC](): Higher is better; unit: SCALAR. - [Avg AUC Gap](): Lower is better; unit: SCALAR. - [Avg Mean PSD](): Lower is better; unit: SCALAR. - [Avg Max PSD](): Lower is better; unit: SCALAR. ## Recorded results | Method | Avg Overall AUC | Result date | Report paper | | --- | --- | --- | --- | | FairDi | 0.905 | Not recorded | 6a191dd6dbd7150506f82afb | | FairDi | 0.9014 | Not recorded | 6a191dd6dbd7150506f82afb | | SWAD | 0.8889 | Not recorded | 6a191dd6dbd7150506f82afb | | SWAD | 0.8867 | Not recorded | 6a191dd6dbd7150506f82afb | | FEBS | 0.8827 | Not recorded | 6a191dd6dbd7150506f82afb | | FIS | 0.8806 | Not recorded | 6a191dd6dbd7150506f82afb | | FIS | 0.8804 | Not recorded | 6a191dd6dbd7150506f82afb | | ERM | 0.8775 | Not recorded | 6a191dd6dbd7150506f82afb | | ERM | 0.8775 | Not recorded | 6a191dd6dbd7150506f82afb | | FEBS | 0.8731 | Not recorded | 6a191dd6dbd7150506f82afb | | FairCLIP-OT | 0.8703 | Not recorded | 6a191dd6dbd7150506f82afb | | FairCLIP-OT | 0.8692 | Not recorded | 6a191dd6dbd7150506f82afb | | FaMI | 0.8668 | Not recorded | 6a191dd6dbd7150506f82afb | | FaMI | 0.8582 | Not recorded | 6a191dd6dbd7150506f82afb | ### FairDi Avg Overall AUC: 0.905. Result ID: 6a193846fbc373592c130dbd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"LHCF"}. This record does not assert independent reproduction. ### FairDi Avg Overall AUC: 0.9014. Result ID: 6a193846fbc373592c130db6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"Classic"}. This record does not assert independent reproduction. ### SWAD Avg Overall AUC: 0.8889. Result ID: 6a193846fbc373592c130db8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"LHCF"}. This record does not assert independent reproduction. ### SWAD Avg Overall AUC: 0.8867. Result ID: 6a193846fbc373592c130db1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"Classic"}. This record does not assert independent reproduction. ### FEBS Avg Overall AUC: 0.8827. Result ID: 6a193846fbc373592c130dbb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"LHCF"}. This record does not assert independent reproduction. ### FIS Avg Overall AUC: 0.8806. Result ID: 6a193846fbc373592c130db2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"Classic"}. This record does not assert independent reproduction. ### FIS Avg Overall AUC: 0.8804. Result ID: 6a193846fbc373592c130db9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"LHCF"}. This record does not assert independent reproduction. ### ERM Avg Overall AUC: 0.8775. Result ID: 6a193846fbc373592c130db0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"Classic"}. This record does not assert independent reproduction. ### ERM Avg Overall AUC: 0.8775. Result ID: 6a193846fbc373592c130db7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"LHCF"}. This record does not assert independent reproduction. ### FEBS Avg Overall AUC: 0.8731. Result ID: 6a193846fbc373592c130db4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"Classic"}. This record does not assert independent reproduction. ### FairCLIP-OT Avg Overall AUC: 0.8703. Result ID: 6a193846fbc373592c130dbc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"LHCF"}. This record does not assert independent reproduction. ### FairCLIP-OT Avg Overall AUC: 0.8692. Result ID: 6a193846fbc373592c130db5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"Classic"}. This record does not assert independent reproduction. ### FaMI Avg Overall AUC: 0.8668. Result ID: 6a193846fbc373592c130dba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"LHCF"}. This record does not assert independent reproduction. ### FaMI Avg Overall AUC: 0.8582. Result ID: 6a193846fbc373592c130db3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"Classic"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.