# Collaborative 3D Object Detection on DAIR-V2X (1% subset)

Source: [Collaborative 3D Object Detection on DAIR-V2X (1% subset)](<https://www.sota2.com/research/sota/collaborative-3d-object-detection-on-dair-v2x-1-percent-subset>)

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

Data updated: 2026-02-26T05:23:25.388Z

Evaluation of Collaborative 3D Object Detection performance using only the 1% labeled subset of the DAIR-V2X dataset, reporting Average Precision at IoU thresholds of 0.50 and 0.70.

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 | Collaborative 3D Object Detection |
| Dataset (including any stated split) | DAIR-V2X 1% labeled data ratio |
| Metric | AP@50 |
| Unit | PERCENT |
| Direction | Higher 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

- [AP@50](<https://www.sota2.com/research/sota/collaborative-3d-object-detection-on-dair-v2x-1-percent-subset.md?metric=AP%4050>): Higher is better; unit: PERCENT.

- [AP@70](<https://www.sota2.com/research/sota/collaborative-3d-object-detection-on-dair-v2x-1-percent-subset.md?metric=AP%4070>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP@50 | Result date | Report paper |
| --- | --- | --- | --- |
| FlowAdapt | 56.1 | Not recorded | 698eaff7c97a0b3e3b5e6641 |
| FlowAdapt† | 53.3 | Not recorded | 698eaff7c97a0b3e3b5e6641 |
| SSF | 50.7 | Not recorded | 698eaff7c97a0b3e3b5e6641 |
| CoPEFT | 50.7 | Not recorded | 698eaff7c97a0b3e3b5e6641 |
| MACP | 45.5 | Not recorded | 698eaff7c97a0b3e3b5e6641 |
| Decoder only | 43.2 | Not recorded | 698eaff7c97a0b3e3b5e6641 |
| None (CoAlign baseline) | 42.9 | Not recorded | 698eaff7c97a0b3e3b5e6641 |
| Adapter | 31.5 | Not recorded | 698eaff7c97a0b3e3b5e6641 |
| Scratch Training | 13.9 | Not recorded | 698eaff7c97a0b3e3b5e6641 |

### FlowAdapt

AP@50: 56.1. Result ID: 699710775698665ec45e02e4.

[Reporting paper](<https://www.sota2.com/research/paper/698eaff7c97a0b3e3b5e6641.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698eaff7c97a0b3e3b5e6641.md>)

Recorded evaluation configuration: {"Parameter":"137,393/13,033,777 = 1.05%"}. This record does not assert independent reproduction.

### FlowAdapt†

AP@50: 53.3. Result ID: 699710775698665ec45e02e3.

[Reporting paper](<https://www.sota2.com/research/paper/698eaff7c97a0b3e3b5e6641.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698eaff7c97a0b3e3b5e6641.md>)

Recorded evaluation configuration: {"Parameter":"95,694/12,992,078 = 0.74%"}. This record does not assert independent reproduction.

### SSF

AP@50: 50.7. Result ID: 699710775698665ec45e02df.

[Reporting paper](<https://www.sota2.com/research/paper/698eaff7c97a0b3e3b5e6641.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e5b1e209131cea3f540.md>)

Recorded evaluation configuration: {"Parameter":"5,780/12,902,164 = 0.04%"}. This record does not assert independent reproduction.

### CoPEFT

AP@50: 50.7. Result ID: 699710775698665ec45e02e2.

[Reporting paper](<https://www.sota2.com/research/paper/698eaff7c97a0b3e3b5e6641.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76fd1e209131cea7041d.md>)

Recorded evaluation configuration: {"Parameter":"111,270/13,007,654 = 0.86%"}. This record does not assert independent reproduction.

### MACP

AP@50: 45.5. Result ID: 699710775698665ec45e02e1.

[Reporting paper](<https://www.sota2.com/research/paper/698eaff7c97a0b3e3b5e6641.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa711d1e209131cea4f30f.md>)

Recorded evaluation configuration: {"Parameter":"43,060/12,939,444 = 0.33%"}. This record does not assert independent reproduction.

### Decoder only

AP@50: 43.2. Result ID: 699710775698665ec45e02de.

[Reporting paper](<https://www.sota2.com/research/paper/698eaff7c97a0b3e3b5e6641.md>)

Recorded evaluation configuration: {"Parameter":"5,140/12,901,524 = 0.04%"}. This record does not assert independent reproduction.

### None (CoAlign baseline)

AP@50: 42.9. Result ID: 699710775698665ec45e02dc.

[Reporting paper](<https://www.sota2.com/research/paper/698eaff7c97a0b3e3b5e6641.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eab1e209131cea4144e.md>)

Recorded evaluation configuration: {"Parameter":"0/12,896,384 = 0.00%"}. This record does not assert independent reproduction.

### Adapter

AP@50: 31.5. Result ID: 699710775698665ec45e02e0.

[Reporting paper](<https://www.sota2.com/research/paper/698eaff7c97a0b3e3b5e6641.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65e31e209131cea0d324.md>)

[Implementation](<https://github.com/google-research/adapter-bert>)

Recorded evaluation configuration: {"Parameter":"42,420/12,938,804 = 0.33%"}. This record does not assert independent reproduction.

### Scratch Training

AP@50: 13.9. Result ID: 699710775698665ec45e02dd.

[Reporting paper](<https://www.sota2.com/research/paper/698eaff7c97a0b3e3b5e6641.md>)

Recorded evaluation configuration: {"Parameter":"12,896,384/12,896,384 = 100.00%"}. This record does not assert independent reproduction.

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