# Object Detection on Waymo 20% train (val)

Source: [Object Detection on Waymo 20% train (val)](<https://www.sota2.com/research/sota/object-detection-on-waymo-20-percent-train-val>)

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

Data updated: 2026-02-26T06:08:12.138Z

Evaluation of Object Detection performance on the 20% training subset validation split of the Waymo dataset, reporting class-specific metrics for Vehicle, Pedestrian, and Cyclist.

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) | Waymo 20% train (val) |
| Metric | Vehicle Detection Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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 Detection Score](<https://www.sota2.com/research/sota/object-detection-on-waymo-20-percent-train-val.md?metric=Vehicle%20Detection%20Score>): Higher is better; unit: PERCENT.

- [Pedestrian Detection Score](<https://www.sota2.com/research/sota/object-detection-on-waymo-20-percent-train-val.md?metric=Pedestrian%20Detection%20Score>): Higher is better; unit: PERCENT.

- [Cyclist Detection Score](<https://www.sota2.com/research/sota/object-detection-on-waymo-20-percent-train-val.md?metric=Cyclist%20Detection%20Score>): Higher is better; unit: PERCENT.

- [Average Detection Score](<https://www.sota2.com/research/sota/object-detection-on-waymo-20-percent-train-val.md?metric=Average%20Detection%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Vehicle Detection Score | Result date | Report paper |
| --- | --- | --- | --- |
| Masked Shape Prediction | 65.12 | Not recorded | 68fa6f421e209131cea44920 |
| Masked Shape Prediction | 64.33 | Not recorded | 68fa6f421e209131cea44920 |
| Masked Shape Prediction | 64.11 | Not recorded | 68fa6f421e209131cea44920 |
| Masked Shape Prediction | 63.99 | Not recorded | 68fa6f421e209131cea44920 |
| CenterPoint | 62.65 | Not recorded | 68fa6f421e209131cea44920 |
| SECOND | 62.02 | Not recorded | 68fa6f421e209131cea44920 |

### Masked Shape Prediction

Vehicle Detection Score: 65.12. Result ID: 6990b11e3a6c314849027c59.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f421e209131cea44920.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f421e209131cea44920.md>)

Recorded evaluation configuration: {"Pre-trained":true,"Backbone":"EQ-Net","Detection Head":"SECOND"}. This record does not assert independent reproduction.

### Masked Shape Prediction

Vehicle Detection Score: 64.33. Result ID: 6990b11e3a6c314849027c58.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f421e209131cea44920.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f421e209131cea44920.md>)

Recorded evaluation configuration: {"Pre-trained":false,"Backbone":"EQ-Net","Detection Head":"SECOND"}. This record does not assert independent reproduction.

### Masked Shape Prediction

Vehicle Detection Score: 64.11. Result ID: 6990b11e3a6c314849027c5c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f421e209131cea44920.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f421e209131cea44920.md>)

Recorded evaluation configuration: {"Pre-trained":true,"Backbone":"EQ-Net","Detection Head":"CenterPoint"}. This record does not assert independent reproduction.

### Masked Shape Prediction

Vehicle Detection Score: 63.99. Result ID: 6990b11e3a6c314849027c5b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f421e209131cea44920.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f421e209131cea44920.md>)

Recorded evaluation configuration: {"Pre-trained":false,"Backbone":"EQ-Net","Detection Head":"CenterPoint"}. This record does not assert independent reproduction.

### CenterPoint

Vehicle Detection Score: 62.65. Result ID: 6990b11e3a6c314849027c5a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f421e209131cea44920.md>)

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

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

Recorded evaluation configuration: {"Pre-trained":false,"Detection Head":"CenterPoint"}. This record does not assert independent reproduction.

### SECOND

Vehicle Detection Score: 62.02. Result ID: 6990b11e3a6c314849027c57.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f421e209131cea44920.md>)

Recorded evaluation configuration: {"Pre-trained":false,"Detection Head":"SECOND"}. This record does not assert independent reproduction.

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