# Long-tailed classification on Lesion-10 (test) Source: [Long-tailed classification on Lesion-10 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:17.593Z Evaluation of long-tailed classification performance on the test split of the Lesion-10 dataset, reporting metrics broken down by head, medium, and tail classes. 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 | Long-tailed classification | | Dataset (including any stated split) | Lesion-10 (test) | | Metric | Accuracy (Head) | | Unit | PERCENT | | 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 - [Accuracy (Head)](): Higher is better; unit: PERCENT. - [Accuracy (Medium)](): Higher is better; unit: PERCENT. - [Accuracy (Tail)](): Higher is better; unit: PERCENT. - [Accuracy (Total)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Head) | Result date | Report paper | | --- | --- | --- | --- | | DB Loss | 88.01 | Not recorded | 68fa69cb1e209131cea24108 | | OLTR | 87.55 | Not recorded | 68fa69cb1e209131cea24108 | | Relational Subsets Knowledge Distillation | 87.22 | Not recorded | 68fa69cb1e209131cea24108 | | Relational Subsets Knowledge Distillation | 86.97 | Not recorded | 68fa69cb1e209131cea24108 | | LDAM | 86.9 | Not recorded | 68fa69cb1e209131cea24108 | | Relational Subsets Knowledge Distillation | 86.87 | Not recorded | 68fa69cb1e209131cea24108 | | ERM Model | 86.84 | Not recorded | 68fa69cb1e209131cea24108 | | Focal Loss | 86.84 | Not recorded | 68fa69cb1e209131cea24108 | | Relational Subsets Knowledge Distillation | 85.73 | Not recorded | 68fa69cb1e209131cea24108 | | Relational Subsets Knowledge Distillation | 85.42 | Not recorded | 68fa69cb1e209131cea24108 | | Relational Subsets Knowledge Distillation | 84.88 | Not recorded | 68fa69cb1e209131cea24108 | | Relational Subsets Knowledge Distillation | 84.15 | Not recorded | 68fa69cb1e209131cea24108 | | RW | 83.42 | Not recorded | 68fa69cb1e209131cea24108 | | RS | 81.42 | Not recorded | 68fa69cb1e209131cea24108 | ### DB Loss Accuracy (Head): 88.01. Result ID: 698de3d3ffc3901de09964b0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### OLTR Accuracy (Head): 87.55. Result ID: 698de3d3ffc3901de09964ae. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Relational Subsets Knowledge Distillation Accuracy (Head): 87.22. Result ID: 698de3d3ffc3901de09964b2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"type":"region-based"}. This record does not assert independent reproduction. ### Relational Subsets Knowledge Distillation Accuracy (Head): 86.97. Result ID: 698de3d3ffc3901de09964b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Combined with":"Focal Loss"}. This record does not assert independent reproduction. ### LDAM Accuracy (Head): 86.9. Result ID: 698de3d3ffc3901de09964af. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Relational Subsets Knowledge Distillation Accuracy (Head): 86.87. Result ID: 698de3d3ffc3901de09964b1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"type":"shot-based"}. This record does not assert independent reproduction. ### ERM Model Accuracy (Head): 86.84. Result ID: 698de3d3ffc3901de09964aa. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Focal Loss Accuracy (Head): 86.84. Result ID: 698de3d3ffc3901de09964ad. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Relational Subsets Knowledge Distillation Accuracy (Head): 85.73. Result ID: 698de3d3ffc3901de09964b5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Combined with":"OLTR"}. This record does not assert independent reproduction. ### Relational Subsets Knowledge Distillation Accuracy (Head): 85.42. Result ID: 698de3d3ffc3901de09964b3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"type":"feature-based"}. This record does not assert independent reproduction. ### Relational Subsets Knowledge Distillation Accuracy (Head): 84.88. Result ID: 698de3d3ffc3901de09964b6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Combined with":"LDAM"}. This record does not assert independent reproduction. ### Relational Subsets Knowledge Distillation Accuracy (Head): 84.15. Result ID: 698de3d3ffc3901de09964b4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Combined with":"DB Loss"}. This record does not assert independent reproduction. ### RW Accuracy (Head): 83.42. Result ID: 698de3d3ffc3901de09964ac. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### RS Accuracy (Head): 81.42. Result ID: 698de3d3ffc3901de09964ab. [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.