# Forgery Detection on Columbia (test)

Source: [Forgery Detection on Columbia (test)](<https://www.sota2.com/research/sota/forgery-detection-on-columbia-test>)

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

Data updated: 2026-02-26T06:09:23.296Z

Evaluation of general Forgery Detection performance on the test split of the Columbia dataset, measured using Mean Average Precision and AUC.

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 | Forgery Detection |
| Dataset (including any stated split) | Columbia (test) |
| Metric | mAP |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [mAP](<https://www.sota2.com/research/sota/forgery-detection-on-columbia-test.md?metric=mAP>): Higher is better; unit: PERCENT.

- [AUC](<https://www.sota2.com/research/sota/forgery-detection-on-columbia-test.md?metric=AUC>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mAP | Result date | Report paper |
| --- | --- | --- | --- |
| Huh et al. | 98 | Not recorded | 68fa676f1e209131cea16391 |
| Huh et al. | 97 | Not recorded | 68fa676f1e209131cea16391 |
| Mean Forensic Similarity | 95 | Not recorded | 68fa676f1e209131cea16391 |
| Bondi et al. | 70 | Not recorded | 68fa676f1e209131cea16391 |
| Huh et al. | 70 | Not recorded | 68fa676f1e209131cea16391 |

### Huh et al.

mAP: 98. Result ID: 698d35318b517eb4331fcb84.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676f1e209131cea16391.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64c91e209131cea069fd.md>)

Recorded evaluation configuration: {"feature":"EXIF metadata"}. This record does not assert independent reproduction.

### Huh et al.

mAP: 97. Result ID: 698d35318b517eb4331fcb83.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676f1e209131cea16391.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64c91e209131cea069fd.md>)

Recorded evaluation configuration: {"feature":"image content"}. This record does not assert independent reproduction.

### Mean Forensic Similarity

mAP: 95. Result ID: 698d35318b517eb4331fcb85.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676f1e209131cea16391.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa676f1e209131cea16391.md>)

[Implementation](<https://www.sota2.com/gitlab.com/MISLgit/forensic-similarity-for-digital-images>)

Recorded evaluation configuration: {"feature":"camera-model"}. This record does not assert independent reproduction.

### Bondi et al.

mAP: 70. Result ID: 698d35318b517eb4331fcb81.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676f1e209131cea16391.md>)

Recorded evaluation configuration: {"F\_dist":0.9,"conf":0.6}. This record does not assert independent reproduction.

### Huh et al.

mAP: 70. Result ID: 698d35318b517eb4331fcb82.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676f1e209131cea16391.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64c91e209131cea069fd.md>)

Recorded evaluation configuration: {"feature":"camera-model"}. This record does not assert independent reproduction.

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