# Object Detection on perciv-scenes-2 (val)

Source: [Object Detection on perciv-scenes-2 (val)](<https://www.sota2.com/research/sota/object-detection-on-perciv-scenes-2-val>)

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

Data updated: 2026-03-11T09:18:39.922Z

Evaluation of standard 2D Object Detection performance on the validation split of the perciv-scenes-2 dataset, reporting overall metrics (mAP, NDS) and class-specific metrics (APcar, APped., APcyc.).

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 | Object Detection |
| Dataset (including any stated split) | perciv-scenes-2 (val) |
| Metric | mAP |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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/object-detection-on-perciv-scenes-2-val.md?metric=mAP>): Higher is better; unit: PERCENT.

- [NDS](<https://www.sota2.com/research/sota/object-detection-on-perciv-scenes-2-val.md?metric=NDS>): Higher is better; unit: PERCENT.

- [AP (car)](<https://www.sota2.com/research/sota/object-detection-on-perciv-scenes-2-val.md?metric=AP%20(car)>): Higher is better; unit: PERCENT.

- [AP (pedestrian)](<https://www.sota2.com/research/sota/object-detection-on-perciv-scenes-2-val.md?metric=AP%20(pedestrian)>): Higher is better; unit: PERCENT.

- [AP (cyclist)](<https://www.sota2.com/research/sota/object-detection-on-perciv-scenes-2-val.md?metric=AP%20(cyclist)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mAP | Result date | Report paper |
| --- | --- | --- | --- |
| DRIFT (attention) | 55.2 | Not recorded | 69b0f70e2d603e6de3e45d58 |
| CenterPoint | 51.8 | Not recorded | 69b0f70e2d603e6de3e45d58 |

### DRIFT (attention)

mAP: 55.2. Result ID: 69b133666dbb7075b95bdf23.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f70e2d603e6de3e45d58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f70e2d603e6de3e45d58.md>)

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

### CenterPoint

mAP: 51.8. Result ID: 69b133666dbb7075b95bdf22.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f70e2d603e6de3e45d58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af91e209131cea2b72c.md>)

[Implementation](<https://github.com/tianweiy/CenterPoint>)

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.