# Multi-concept Erasure on MS-COCO 10 celebrities erasure scenario

Source: [Multi-concept Erasure on MS-COCO 10 celebrities erasure scenario](<https://www.sota2.com/research/sota/multi-concept-erasure-on-ms-coco-10-celebrities-erasure-scenario>)

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

Data updated: 2026-03-04T08:08:05.085Z

Evaluation of Multi-concept erasure performance on the MS-COCO 10 celebrities erasure scenario dataset, measured by CS and FID.

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 | Multi-concept erasure |
| Dataset (including any stated split) | MS-COCO 10 celebrities erasure scenario |
| Metric | CS |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [CS](<https://www.sota2.com/research/sota/multi-concept-erasure-on-ms-coco-10-celebrities-erasure-scenario.md?metric=CS>): Higher is better; unit: SCALAR.

- [FID](<https://www.sota2.com/research/sota/multi-concept-erasure-on-ms-coco-10-celebrities-erasure-scenario.md?metric=FID>): Lower is better; unit: SCALAR.

## Recorded results

| Method | CS | Result date | Report paper |
| --- | --- | --- | --- |
| SD v1.4 | 26.53 | Not recorded | 68fa7c231e209131cea8ca66 |
| SPEED | 26.47 | Not recorded | 68fa7c231e209131cea8ca66 |
| MACE | 26.36 | Not recorded | 68fa7c231e209131cea8ca66 |
| ConAbl | 25.6 | Not recorded | 68fa7c231e209131cea8ca66 |
| UCE | 24.07 | Not recorded | 68fa7c231e209131cea8ca66 |
| RECE | 16.75 | Not recorded | 68fa7c231e209131cea8ca66 |

### SD v1.4

CS: 26.53. Result ID: 69a7e8626dbb7075b94c9ff6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c231e209131cea8ca66.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SPEED

CS: 26.47. Result ID: 69a7e8626dbb7075b94c9ffb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c231e209131cea8ca66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c231e209131cea8ca66.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MACE

CS: 26.36. Result ID: 69a7e8626dbb7075b94c9ffa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c231e209131cea8ca66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72731e209131cea566f7.md>)

[Implementation](<https://github.com/Shilin-LU/MACE>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ConAbl

CS: 25.6. Result ID: 69a7e8626dbb7075b94c9ff7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c231e209131cea8ca66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa705c1e209131cea4a98a.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### UCE

CS: 24.07. Result ID: 69a7e8626dbb7075b94c9ff8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c231e209131cea8ca66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa755b1e209131cea67702.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RECE

CS: 16.75. Result ID: 69a7e8626dbb7075b94c9ff9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c231e209131cea8ca66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e49.md>)

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.