# Object Detection on DAIR-V2X (test)

Source: [Object Detection on DAIR-V2X (test)](<https://www.sota2.com/research/sota/object-detection-on-dair-v2x-test>)

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

Data updated: 2026-02-26T05:23:23.394Z

Evaluation of 2D Object Detection performance on the test split of the DAIR-V2X dataset, reporting Average Precision (AP) metrics at IoU thresholds of 0.5 and 0.7.

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) | DAIR-V2X (test) |
| Metric | AP@0.5 |
| 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

- [AP@0.5](<https://www.sota2.com/research/sota/object-detection-on-dair-v2x-test.md?metric=AP%400.5>): Higher is better; unit: PERCENT.

- [AP@0.7](<https://www.sota2.com/research/sota/object-detection-on-dair-v2x-test.md?metric=AP%400.7>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP@0.5 | Result date | Report paper |
| --- | --- | --- | --- |
| Upperbound | 59.43 | Not recorded | 68fa7a2d1e209131cea81912 |
| CP-uniGuard | 58.31 | Not recorded | 68fa7a2d1e209131cea81912 |
| AdvTrain | 50.21 | Not recorded | 68fa7a2d1e209131cea81912 |
| ROBOSAC | 42.19 | Not recorded | 68fa7a2d1e209131cea81912 |
| No Defense | 36.55 | Not recorded | 68fa7a2d1e209131cea81912 |

### Upperbound

AP@0.5: 59.43. Result ID: 699a485d5698665ec4cfb911.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a2d1e209131cea81912.md>)

Recorded evaluation configuration: {"Note":"Collaborative perception with all benign agents"}. This record does not assert independent reproduction.

### CP-uniGuard

AP@0.5: 58.31. Result ID: 699a485d5698665ec4cfb910.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a2d1e209131cea81912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a2d1e209131cea81912.md>)

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

### AdvTrain

AP@0.5: 50.21. Result ID: 699a485d5698665ec4cfb90e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a2d1e209131cea81912.md>)

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

### ROBOSAC

AP@0.5: 42.19. Result ID: 699a485d5698665ec4cfb90f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a2d1e209131cea81912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70541e209131cea4a47c.md>)

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

### No Defense

AP@0.5: 36.55. Result ID: 699a485d5698665ec4cfb90d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a2d1e209131cea81912.md>)

Recorded evaluation configuration: {"Attack":"PGD Attack"}. This record does not assert independent reproduction.

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