# Object Detection on Waymo Open Dataset

Source: [Object Detection on Waymo Open Dataset](<https://www.sota2.com/research/sota/object-detection-on-waymo-open-dataset>)

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

Data updated: 2026-02-26T05:23:06.908Z

Evaluation of Object Detection performance on the Waymo Open Dataset, reporting AP metrics across Level 1 and Level 2 difficulty settings.

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 Open Dataset |
| Metric | AP (L1) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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 (L1)](<https://www.sota2.com/research/sota/object-detection-on-waymo-open-dataset.md?metric=AP%20(L1)>): Higher is better; unit: PERCENT.

- [AP (L2)](<https://www.sota2.com/research/sota/object-detection-on-waymo-open-dataset.md?metric=AP%20(L2)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP (L1) | Result date | Report paper |
| --- | --- | --- | --- |
| Cascade FRCNN-RS | 71.2 | Not recorded | 68fa6a471e209131cea27495 |
| Cascade FRCNN-RS | 70.5 | Not recorded | 68fa6a471e209131cea27495 |
| FRCNN-RS | 70 | Not recorded | 68fa6a471e209131cea27495 |
| FRCNN-RS | 69.5 | Not recorded | 68fa6a471e209131cea27495 |
| Cascade FRCNN-RS | 68.6 | Not recorded | 68fa6a471e209131cea27495 |
| FRCNN-RS | 68.1 | Not recorded | 68fa6a471e209131cea27495 |
| RetinaNet-RS | 64.5 | Not recorded | 68fa6a471e209131cea27495 |

### Cascade FRCNN-RS

AP (L1): 71.2. Result ID: 698e282affc3901de09b3ef1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a471e209131cea27495.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a471e209131cea27495.md>)

[Implementation](<https://github.com/tensorflow/models/tree/master/official/vision/beta>)

Recorded evaluation configuration: {"Backbone":"SpineNet143L","Train Resolution":"896x1664","Eval Resolution":"1280x2400"}. This record does not assert independent reproduction.

### Cascade FRCNN-RS

AP (L1): 70.5. Result ID: 698e282affc3901de09b3ef0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a471e209131cea27495.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a471e209131cea27495.md>)

[Implementation](<https://github.com/tensorflow/models/tree/master/official/vision/beta>)

Recorded evaluation configuration: {"Backbone":"SpineNet143L","Train Resolution":"896x1664","Eval Resolution":"1024x1920"}. This record does not assert independent reproduction.

### FRCNN-RS

AP (L1): 70. Result ID: 698e282affc3901de09b3eee.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a471e209131cea27495.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62191e209131ce9f79f3.md>)

[Implementation](<https://github.com/rbgirshick/fast-rcnn>)

Recorded evaluation configuration: {"Backbone":"SpineNet143L","Train Resolution":"896x1664","Eval Resolution":"1280x2400"}. This record does not assert independent reproduction.

### FRCNN-RS

AP (L1): 69.5. Result ID: 698e282affc3901de09b3eed.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a471e209131cea27495.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62191e209131ce9f79f3.md>)

[Implementation](<https://github.com/rbgirshick/fast-rcnn>)

Recorded evaluation configuration: {"Backbone":"SpineNet143L","Train Resolution":"896x1664","Eval Resolution":"1024x1920"}. This record does not assert independent reproduction.

### Cascade FRCNN-RS

AP (L1): 68.6. Result ID: 698e282affc3901de09b3eef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a471e209131cea27495.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a471e209131cea27495.md>)

[Implementation](<https://github.com/tensorflow/models/tree/master/official/vision/beta>)

Recorded evaluation configuration: {"Backbone":"SpineNet143L","Train Resolution":"896x1664","Eval Resolution":"896x1664"}. This record does not assert independent reproduction.

### FRCNN-RS

AP (L1): 68.1. Result ID: 698e282affc3901de09b3eec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a471e209131cea27495.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62191e209131ce9f79f3.md>)

[Implementation](<https://github.com/rbgirshick/fast-rcnn>)

Recorded evaluation configuration: {"Backbone":"SpineNet143L","Train Resolution":"896x1664","Eval Resolution":"896x1664"}. This record does not assert independent reproduction.

### RetinaNet-RS

AP (L1): 64.5. Result ID: 698e282affc3901de09b3eeb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a471e209131cea27495.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a471e209131cea27495.md>)

[Implementation](<https://github.com/tensorflow/models/tree/master/official/vision/beta>)

Recorded evaluation configuration: {"Backbone":"SpineNet143L","Train Resolution":"896x1664","Eval Resolution":"896x1664"}. This record does not assert independent reproduction.

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