# Pedestrian Detection on CityPersons Reasonable (R)

Source: [Pedestrian Detection on CityPersons Reasonable (R)](<https://www.sota2.com/research/sota/pedestrian-detection-on-citypersons-reasonable-r>)

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

Data updated: 2026-02-26T05:52:53.606Z

Evaluation of Pedestrian Detection performance on the CityPersons dataset, specifically focusing on the 'Reasonable' occlusion setting, reporting Miss Rate metrics.

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 | Pedestrian Detection |
| Dataset (including any stated split) | CityPersons reasonable (R) |
| Metric | Miss Rate |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 9 of 9 |
| 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

- [Miss Rate](<https://www.sota2.com/research/sota/pedestrian-detection-on-citypersons-reasonable-r.md?metric=Miss%20Rate>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Miss Rate | Result date | Report paper |
| --- | --- | --- | --- |
| Faster R-CNN (ours) | 12.7 | Not recorded | 68fa69d31e209131cea246ff |
| Adaptive-NMS | 12.9 | Not recorded | 68fa69d31e209131cea246ff |
| Rep Loss | 13.2 | Not recorded | 68fa69d31e209131cea246ff |
| FreeAnchor (ours) | 13.6 | Not recorded | 68fa69d31e209131cea246ff |
| RFB Net | 13.9 | Not recorded | 68fa69d31e209131cea246ff |
| TLL | 14.4 | Not recorded | 68fa69d31e209131cea246ff |
| Faster R-CNN | 14.6 | Not recorded | 68fa69d31e209131cea246ff |
| FreeAnchor | 14.8 | Not recorded | 68fa69d31e209131cea246ff |
| RetinaNet | 15.6 | Not recorded | 68fa69d31e209131cea246ff |

### Faster R-CNN (ours)

Miss Rate: 12.7. Result ID: 698deba8ffc3901de09991e0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69d31e209131cea246ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69d31e209131cea246ff.md>)

Recorded evaluation configuration: {"Architecture Type":"Two-stage","Resolution":"2048 x 1024"}. This record does not assert independent reproduction.

### Adaptive-NMS

Miss Rate: 12.9. Result ID: 698deba8ffc3901de09991df.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69d31e209131cea246ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65a01e209131cea0b5f2.md>)

Recorded evaluation configuration: {"Architecture Type":"Two-stage","Resolution":"2048 x 1024"}. This record does not assert independent reproduction.

### Rep Loss

Miss Rate: 13.2. Result ID: 698deba8ffc3901de09991de.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69d31e209131cea246ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64311e209131cea035a2.md>)

Recorded evaluation configuration: {"Architecture Type":"Two-stage","Resolution":"2048 x 1024"}. This record does not assert independent reproduction.

### FreeAnchor (ours)

Miss Rate: 13.6. Result ID: 698deba8ffc3901de09991dc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69d31e209131cea246ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69d31e209131cea246ff.md>)

Recorded evaluation configuration: {"Architecture Type":"Single-stage","Resolution":"2048 x 1024"}. This record does not assert independent reproduction.

### RFB Net

Miss Rate: 13.9. Result ID: 698deba8ffc3901de09991db.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69d31e209131cea246ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa649b1e209131cea05834.md>)

Recorded evaluation configuration: {"Architecture Type":"Single-stage","Resolution":"2048 x 1024"}. This record does not assert independent reproduction.

### TLL

Miss Rate: 14.4. Result ID: 698deba8ffc3901de09991da.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69d31e209131cea246ff.md>)

Recorded evaluation configuration: {"Architecture Type":"Single-stage","Resolution":"2048 x 1024"}. This record does not assert independent reproduction.

### Faster R-CNN

Miss Rate: 14.6. Result ID: 698deba8ffc3901de09991dd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69d31e209131cea246ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64311e209131cea035a2.md>)

Recorded evaluation configuration: {"Architecture Type":"Two-stage","Resolution":"2048 x 1024"}. This record does not assert independent reproduction.

### FreeAnchor

Miss Rate: 14.8. Result ID: 698deba8ffc3901de09991d9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69d31e209131cea246ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66ae1e209131cea11adb.md>)

[Implementation](<https://github.com/zhangxiaosong18/FreeAnchor>)

Recorded evaluation configuration: {"Architecture Type":"Single-stage","Resolution":"2048 x 1024"}. This record does not assert independent reproduction.

### RetinaNet

Miss Rate: 15.6. Result ID: 698deba8ffc3901de09991d8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69d31e209131cea246ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa640c1e209131cea02556.md>)

[Implementation](<https://github.com/facebookresearch/Detectron>)

Recorded evaluation configuration: {"Architecture Type":"Single-stage","Resolution":"2048 x 1024"}. This record does not assert independent reproduction.

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