# Skin Cancer Classification on ISIC, HAM, and DERM7 (small external)

Source: [Skin Cancer Classification on ISIC, HAM, and DERM7 (small external)](<https://www.sota2.com/research/sota/skin-cancer-classification-on-isic-ham-and-derm7-small-external>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-16T08:28:58.463Z

Evaluation of skin cancer classification performance using a combined external dataset comprising subsets of ISIC, HAM, and DERM7 data.

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 | Skin Cancer Classification |
| Dataset (including any stated split) | ISIC, HAM, and DERM7 (small external) |
| Metric | Average Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Average Accuracy](<https://www.sota2.com/research/sota/skin-cancer-classification-on-isic-ham-and-derm7-small-external.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

- [BWT Score](<https://www.sota2.com/research/sota/skin-cancer-classification-on-isic-ham-and-derm7-small-external.md?metric=BWT%20Score>): Higher is better; unit: SCALAR.

- [Average F1 Score](<https://www.sota2.com/research/sota/skin-cancer-classification-on-isic-ham-and-derm7-small-external.md?metric=Average%20F1%20Score>): Higher is better; unit: PERCENT.

- [CAR (Threshold 0.5)](<https://www.sota2.com/research/sota/skin-cancer-classification-on-isic-ham-and-derm7-small-external.md?metric=CAR%20(Threshold%200.5)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Average Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| UniPrompt-CL | 73.2 | Not recorded | 68fa7ab01e209131cea84a22 |
| OS++ | 72.5 | Not recorded | 68fa7ab01e209131cea84a22 |
| DER++ | 72.2 | Not recorded | 68fa7ab01e209131cea84a22 |
| Coda-Prompt | 71.3 | Not recorded | 68fa7ab01e209131cea84a22 |
| Online EWC | 70.8 | Not recorded | 68fa7ab01e209131cea84a22 |
| OS | 68.2 | Not recorded | 68fa7ab01e209131cea84a22 |
| Dual-prompt | 63.7 | Not recorded | 68fa7ab01e209131cea84a22 |
| MoE-Adapters | 59.7 | Not recorded | 68fa7ab01e209131cea84a22 |

### UniPrompt-CL

Average Accuracy: 73.2. Result ID: 69b7bd5847f34ce9249f5345.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ab01e209131cea84a22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ab01e209131cea84a22.md>)

Recorded evaluation configuration: {"GFLOPs":"44.17"}. This record does not assert independent reproduction.

### OS++

Average Accuracy: 72.5. Result ID: 69b7bd5847f34ce9249f533f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ab01e209131cea84a22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa725b1e209131cea55ea9.md>)

Recorded evaluation configuration: {"GFLOPs":"51.12"}. This record does not assert independent reproduction.

### DER++

Average Accuracy: 72.2. Result ID: 69b7bd5847f34ce9249f5343.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ab01e209131cea84a22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a11e209131cea1d3e2.md>)

[Implementation](<https://github.com/aimagelab/mammoth>)

Recorded evaluation configuration: {"GFLOPs":"168.02"}. This record does not assert independent reproduction.

### Coda-Prompt

Average Accuracy: 71.3. Result ID: 69b7bd5847f34ce9249f5341.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ab01e209131cea84a22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee41e209131cea42add.md>)

Recorded evaluation configuration: {"GFLOPs":"134.33"}. This record does not assert independent reproduction.

### Online EWC

Average Accuracy: 70.8. Result ID: 69b7bd5847f34ce9249f5344.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ab01e209131cea84a22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64881e209131cea053e1.md>)

Recorded evaluation configuration: {"GFLOPs":"100.62"}. This record does not assert independent reproduction.

### OS

Average Accuracy: 68.2. Result ID: 69b7bd5847f34ce9249f533e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ab01e209131cea84a22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa725b1e209131cea55ea9.md>)

Recorded evaluation configuration: {"GFLOPs":"34.26"}. This record does not assert independent reproduction.

### Dual-prompt

Average Accuracy: 63.7. Result ID: 69b7bd5847f34ce9249f5342.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ab01e209131cea84a22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d341e209131cea38614.md>)

Recorded evaluation configuration: {"GFLOPs":"105.05"}. This record does not assert independent reproduction.

### MoE-Adapters

Average Accuracy: 59.7. Result ID: 69b7bd5847f34ce9249f5340.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ab01e209131cea84a22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73661e209131cea5c39b.md>)

Recorded evaluation configuration: {"GFLOPs":"105.64"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
