# 3D Object Detection on ONCE 500K unlabeled Samples (Medium)

Source: [3D Object Detection on ONCE 500K unlabeled Samples (Medium)](<https://www.sota2.com/research/sota/3d-object-detection-on-once-500k-unlabeled-samples-medium>)

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

Data updated: 2026-02-26T06:08:11.941Z

Evaluation of 3D Object Detection performance using the 500K unlabeled samples designated as the Medium difficulty subset of the ONCE dataset. Metrics include Average Precision (AP) segmented by object class (Vehicle, Pedestrian, Cyclist) and distance ranges (0-30m, 30-50m, 50m-inf).

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 | 3D Object Detection |
| Dataset (including any stated split) | ONCE 500K unlabeled Samples (Medium) |
| Metric | Vehicle AP (Overall) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Vehicle AP (Overall)](<https://www.sota2.com/research/sota/3d-object-detection-on-once-500k-unlabeled-samples-medium.md?metric=Vehicle%20AP%20(Overall)>): Higher is better; unit: PERCENT.

- [Vehicle AP (0-30m)](<https://www.sota2.com/research/sota/3d-object-detection-on-once-500k-unlabeled-samples-medium.md?metric=Vehicle%20AP%20(0-30m)>): Higher is better; unit: PERCENT.

- [Vehicle AP (30-50m)](<https://www.sota2.com/research/sota/3d-object-detection-on-once-500k-unlabeled-samples-medium.md?metric=Vehicle%20AP%20(30-50m)>): Higher is better; unit: PERCENT.

- [Vehicle AP (50m+ Inf)](<https://www.sota2.com/research/sota/3d-object-detection-on-once-500k-unlabeled-samples-medium.md?metric=Vehicle%20AP%20(50m%2B%20Inf)>): Higher is better; unit: PERCENT.

- [Pedestrian AP (Overall)](<https://www.sota2.com/research/sota/3d-object-detection-on-once-500k-unlabeled-samples-medium.md?metric=Pedestrian%20AP%20(Overall)>): Higher is better; unit: PERCENT.

- [Pedestrian AP (0-30m)](<https://www.sota2.com/research/sota/3d-object-detection-on-once-500k-unlabeled-samples-medium.md?metric=Pedestrian%20AP%20(0-30m)>): Higher is better; unit: PERCENT.

- [Pedestrian AP (30-50m)](<https://www.sota2.com/research/sota/3d-object-detection-on-once-500k-unlabeled-samples-medium.md?metric=Pedestrian%20AP%20(30-50m)>): Higher is better; unit: PERCENT.

- [Pedestrian AP (50m+ Inf)](<https://www.sota2.com/research/sota/3d-object-detection-on-once-500k-unlabeled-samples-medium.md?metric=Pedestrian%20AP%20(50m%2B%20Inf)>): Higher is better; unit: PERCENT.

- [Cyclist AP (Overall)](<https://www.sota2.com/research/sota/3d-object-detection-on-once-500k-unlabeled-samples-medium.md?metric=Cyclist%20AP%20(Overall)>): Higher is better; unit: PERCENT.

- [Cyclist AP (0-30m)](<https://www.sota2.com/research/sota/3d-object-detection-on-once-500k-unlabeled-samples-medium.md?metric=Cyclist%20AP%20(0-30m)>): Higher is better; unit: PERCENT.

- [Cyclist AP (30-50m)](<https://www.sota2.com/research/sota/3d-object-detection-on-once-500k-unlabeled-samples-medium.md?metric=Cyclist%20AP%20(30-50m)>): Higher is better; unit: PERCENT.

- [Cyclist AP (50m+ Inf)](<https://www.sota2.com/research/sota/3d-object-detection-on-once-500k-unlabeled-samples-medium.md?metric=Cyclist%20AP%20(50m%2B%20Inf)>): Higher is better; unit: PERCENT.

- [mAP (Overall)](<https://www.sota2.com/research/sota/3d-object-detection-on-once-500k-unlabeled-samples-medium.md?metric=mAP%20(Overall)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Vehicle AP (Overall) | Result date | Report paper |
| --- | --- | --- | --- |
| PTPM + GeoTeacher | 79.51 | Not recorded | 69535c9153fdd5c36173da0c |
| ProficientTeacher + GeoTeacher | 78.94 | Not recorded | 69535c9153fdd5c36173da0c |
| ProficientTeacher | 78.07 | Not recorded | 69535c9153fdd5c36173da0c |
| NoiseDet | 77.14 | Not recorded | 69535c9153fdd5c36173da0c |
| PTPM | 76.66 | Not recorded | 69535c9153fdd5c36173da0c |
| 3DIoUMatch | 75.69 | Not recorded | 69535c9153fdd5c36173da0c |
| Noisy Student | 75.53 | Not recorded | 69535c9153fdd5c36173da0c |
| SESS | 72.11 | Not recorded | 69535c9153fdd5c36173da0c |

### PTPM + GeoTeacher

Vehicle AP (Overall): 79.51. Result ID: 699802a45698665ec45c2537.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9153fdd5c36173da0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69535c9153fdd5c36173da0c.md>)

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

### ProficientTeacher + GeoTeacher

Vehicle AP (Overall): 78.94. Result ID: 699802a45698665ec45c2535.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9153fdd5c36173da0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69535c9153fdd5c36173da0c.md>)

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

### ProficientTeacher

Vehicle AP (Overall): 78.07. Result ID: 699802a45698665ec45c2534.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9153fdd5c36173da0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d1e1e209131cea37e4f.md>)

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

### NoiseDet

Vehicle AP (Overall): 77.14. Result ID: 699802a45698665ec45c2533.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9153fdd5c36173da0c.md>)

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

### PTPM

Vehicle AP (Overall): 76.66. Result ID: 699802a45698665ec45c2536.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9153fdd5c36173da0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74261e209131cea6005f.md>)

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

### 3DIoUMatch

Vehicle AP (Overall): 75.69. Result ID: 699802a45698665ec45c2532.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9153fdd5c36173da0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a571e209131cea2788b.md>)

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

### Noisy Student

Vehicle AP (Overall): 75.53. Result ID: 699802a45698665ec45c2530.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9153fdd5c36173da0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67cc1e209131cea187d2.md>)

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

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

### SESS

Vehicle AP (Overall): 72.11. Result ID: 699802a45698665ec45c2531.

[Reporting paper](<https://www.sota2.com/research/paper/69535c9153fdd5c36173da0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69931e209131cea22c48.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.
