# Localized Detection on BR-Gen (test)

Source: [Localized Detection on BR-Gen (test)](<https://www.sota2.com/research/sota/localized-detection-on-br-gen-test>)

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

Data updated: 2026-03-11T07:54:21.182Z

Evaluation of Localized Detection performance on the test split of the BR-Gen dataset, reporting metrics such as Recall@50, F1, and IoU.

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 | Localized Detection |
| Dataset (including any stated split) | BR-Gen (test) |
| Metric | Real Recall@50 |
| Unit | PERCENT |
| 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

- [Real Recall@50](<https://www.sota2.com/research/sota/localized-detection-on-br-gen-test.md?metric=Real%20Recall%4050>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/localized-detection-on-br-gen-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

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

- [Recall@50](<https://www.sota2.com/research/sota/localized-detection-on-br-gen-test.md?metric=Recall%4050>): Higher is better; unit: PERCENT.

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

- [GAN Recall@50](<https://www.sota2.com/research/sota/localized-detection-on-br-gen-test.md?metric=GAN%20Recall%4050>): Higher is better; unit: PERCENT.

- [Diffusion Recall@50](<https://www.sota2.com/research/sota/localized-detection-on-br-gen-test.md?metric=Diffusion%20Recall%4050>): Higher is better; unit: PERCENT.

- [Background Recall@50](<https://www.sota2.com/research/sota/localized-detection-on-br-gen-test.md?metric=Background%20Recall%4050>): Higher is better; unit: PERCENT.

- [Stuff Recall@50](<https://www.sota2.com/research/sota/localized-detection-on-br-gen-test.md?metric=Stuff%20Recall%4050>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Real Recall@50 | Result date | Report paper |
| --- | --- | --- | --- |
| NFA-ViT | 99.2 | Not recorded | 68fa78241e209131cea76fb5 |
| SparseViT | 98.4 | Not recorded | 68fa78241e209131cea76fb5 |
| Trufor | 94.4 | Not recorded | 68fa78241e209131cea76fb5 |
| PSCC-Net | 93.5 | Not recorded | 68fa78241e209131cea76fb5 |
| MVSS-Net | 90.3 | Not recorded | 68fa78241e209131cea76fb5 |
| ManTranet | 85.3 | Not recorded | 68fa78241e209131cea76fb5 |

### NFA-ViT

Real Recall@50: 99.2. Result ID: 69b11faa6dbb7075b95b4c50.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78241e209131cea76fb5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78241e209131cea76fb5.md>)

Recorded evaluation configuration: {"Backbone":"SegFormer (b2 image encoder, b0 noise encoder)"}. This record does not assert independent reproduction.

### SparseViT

Real Recall@50: 98.4. Result ID: 69b11faa6dbb7075b95b4c4f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78241e209131cea76fb5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa765b1e209131cea6c95b.md>)

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

### Trufor

Real Recall@50: 94.4. Result ID: 69b11faa6dbb7075b95b4c4e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78241e209131cea76fb5.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

Real Recall@50: 93.5. Result ID: 69b11faa6dbb7075b95b4c4d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78241e209131cea76fb5.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.

### MVSS-Net

Real Recall@50: 90.3. Result ID: 69b11faa6dbb7075b95b4c4c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78241e209131cea76fb5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cba1e209131cea35a37.md>)

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

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

### ManTranet

Real Recall@50: 85.3. Result ID: 69b11faa6dbb7075b95b4c4b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78241e209131cea76fb5.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.
