# Image Forgery Localization on CocoGlide COCO 2017 (val)

Source: [Image Forgery Localization on CocoGlide COCO 2017 (val)](<https://www.sota2.com/research/sota/image-forgery-localization-on-cocoglide-coco-2017-val>)

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

Data updated: 2026-02-26T05:43:53.164Z

Evaluation of Image Forgery Localization performance on the validation split of the CocoGlide COCO 2017 dataset, reporting F1 scores.

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 | Image forgery localization |
| Dataset (including any stated split) | CocoGlide COCO 2017 (val) |
| Metric | F1 Score (Best) |
| 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

- [F1 Score (Best)](<https://www.sota2.com/research/sota/image-forgery-localization-on-cocoglide-coco-2017-val.md?metric=F1%20Score%20(Best)>): Higher is better; unit: SCALAR.

- [F1 Score (Fixed)](<https://www.sota2.com/research/sota/image-forgery-localization-on-cocoglide-coco-2017-val.md?metric=F1%20Score%20(Fixed)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | F1 Score (Best) | Result date | Report paper |
| --- | --- | --- | --- |
| TruFor | 0.72 | Not recorded | 68fa6f7f1e209131cea45fb0 |
| PSCC-Net | 0.685 | Not recorded | 68fa6f7f1e209131cea45fb0 |
| ManTraNet | 0.673 | Not recorded | 68fa6f7f1e209131cea45fb0 |
| MVSS-Net | 0.642 | Not recorded | 68fa6f7f1e209131cea45fb0 |
| CAT-Net v2 | 0.603 | Not recorded | 68fa6f7f1e209131cea45fb0 |
| IF-OSN | 0.589 | Not recorded | 68fa6f7f1e209131cea45fb0 |
| CR-CNN | 0.577 | Not recorded | 68fa6f7f1e209131cea45fb0 |
| RRU-Net | 0.504 | Not recorded | 68fa6f7f1e209131cea45fb0 |
| Splicebuster | 0.434 | Not recorded | 68fa6f7f1e209131cea45fb0 |
| EXIF-SC | 0.424 | Not recorded | 68fa6f7f1e209131cea45fb0 |
| Noiseprint | 0.405 | Not recorded | 68fa6f7f1e209131cea45fb0 |
| AdaCFA | 0.357 | Not recorded | 68fa6f7f1e209131cea45fb0 |
| SPAN | 0.35 | Not recorded | 68fa6f7f1e209131cea45fb0 |
| ADQ | 0.302 | Not recorded | 68fa6f7f1e209131cea45fb0 |

### TruFor

F1 Score (Best): 0.72. Result ID: 6990db313a6c31484903cdc5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fb0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fb0.md>)

[Implementation](<https://grip-unina.github.io/TruFor/>)

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

### PSCC-Net

F1 Score (Best): 0.685. Result ID: 6990db313a6c31484903cdc3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fb0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d391e209131cea3890a.md>)

[Implementation](<https://github.com/proteus1991/PSCC-Net>)

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

### ManTraNet

F1 Score (Best): 0.673. Result ID: 6990db313a6c31484903cdbd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fb0.md>)

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

### MVSS-Net

F1 Score (Best): 0.642. Result ID: 6990db313a6c31484903cdc2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fb0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a751e209131cea28443.md>)

[Implementation](<https://github.com/dong03/MVSS-Net>)

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

### CAT-Net v2

F1 Score (Best): 0.603. Result ID: 6990db313a6c31484903cdc0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fb0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c9b1e209131cea34da1.md>)

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

### IF-OSN

F1 Score (Best): 0.589. Result ID: 6990db313a6c31484903cdc1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fb0.md>)

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

### CR-CNN

F1 Score (Best): 0.577. Result ID: 6990db313a6c31484903cdbb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fb0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67331e209131cea14ae7.md>)

[Implementation](<https://github.com/HuizhouLi/Constrained-R-CNN>)

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

### RRU-Net

F1 Score (Best): 0.504. Result ID: 6990db313a6c31484903cdbc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fb0.md>)

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

### Splicebuster

F1 Score (Best): 0.434. Result ID: 6990db313a6c31484903cdb9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fb0.md>)

Recorded evaluation configuration: {"normalization":"between 0 and 1"}. This record does not assert independent reproduction.

### EXIF-SC

F1 Score (Best): 0.424. Result ID: 6990db313a6c31484903cdba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fb0.md>)

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

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

### Noiseprint

F1 Score (Best): 0.405. Result ID: 6990db313a6c31484903cdc4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fb0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64bc1e209131cea06225.md>)

Recorded evaluation configuration: {"normalization":"between 0 and 1"}. This record does not assert independent reproduction.

### AdaCFA

F1 Score (Best): 0.357. Result ID: 6990db313a6c31484903cdbf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fb0.md>)

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

### SPAN

F1 Score (Best): 0.35. Result ID: 6990db313a6c31484903cdbe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fb0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa691a1e209131cea2041f.md>)

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

### ADQ

F1 Score (Best): 0.302. Result ID: 6990db313a6c31484903cdb8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fb0.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.