# BEV Semantic Segmentation on nuScenes Singapore -\> Boston 1.0 (test val)

Source: [BEV Semantic Segmentation on nuScenes Singapore -\> Boston 1.0 (test val)](<https://www.sota2.com/research/sota/bev-semantic-segmentation-on-nuscenes-singapore-boston-1-0-test-val>)

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

Data updated: 2026-02-26T06:10:55.955Z

Evaluation of Bird's Eye View (BEV) Semantic Segmentation performance on the nuScenes dataset, specifically focusing on the domain transfer scenario from Singapore source data to the Boston 1.0 target split (test/val). Metrics include class-specific IoUs for drivable areas, pedestrians, vehicles, and overall mIoU.

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 | BEV Semantic Segmentation |
| Dataset (including any stated split) | nuScenes Singapore -\> Boston 1.0 (test val) |
| Metric | mIoU (Drivable Area) |
| 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

- [mIoU (Drivable Area)](<https://www.sota2.com/research/sota/bev-semantic-segmentation-on-nuscenes-singapore-boston-1-0-test-val.md?metric=mIoU%20(Drivable%20Area)>): Higher is better; unit: PERCENT.

- [mIoU (Pedestrian)](<https://www.sota2.com/research/sota/bev-semantic-segmentation-on-nuscenes-singapore-boston-1-0-test-val.md?metric=mIoU%20(Pedestrian)>): Higher is better; unit: PERCENT.

- [mIoU (Walker)](<https://www.sota2.com/research/sota/bev-semantic-segmentation-on-nuscenes-singapore-boston-1-0-test-val.md?metric=mIoU%20(Walker)>): Higher is better; unit: PERCENT.

- [mIoU (Stop Region)](<https://www.sota2.com/research/sota/bev-semantic-segmentation-on-nuscenes-singapore-boston-1-0-test-val.md?metric=mIoU%20(Stop%20Region)>): Higher is better; unit: PERCENT.

- [mIoU (Car)](<https://www.sota2.com/research/sota/bev-semantic-segmentation-on-nuscenes-singapore-boston-1-0-test-val.md?metric=mIoU%20(Car)>): Higher is better; unit: PERCENT.

- [mIoU (Div.)](<https://www.sota2.com/research/sota/bev-semantic-segmentation-on-nuscenes-singapore-boston-1-0-test-val.md?metric=mIoU%20(Div.)>): Higher is better; unit: PERCENT.

- [mIoU](<https://www.sota2.com/research/sota/bev-semantic-segmentation-on-nuscenes-singapore-boston-1-0-test-val.md?metric=mIoU>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU (Drivable Area) | Result date | Report paper |
| --- | --- | --- | --- |
| NRSeg | 61.4 | Not recorded | 68fa79d41e209131cea7f934 |
| MT+PV | 48 | Not recorded | 68fa79d41e209131cea7f934 |
| PCT\* | 47 | Not recorded | 68fa79d41e209131cea7f934 |
| DualCross | 45.7 | Not recorded | 68fa79d41e209131cea7f934 |
| Source Only | 44.7 | Not recorded | 68fa79d41e209131cea7f934 |
| DomainADV\* | 35.7 | Not recorded | 68fa79d41e209131cea7f934 |

### NRSeg

mIoU (Drivable Area): 61.4. Result ID: 699ebaa25698665ec489b7a8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d41e209131cea7f934.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79d41e209131cea7f934.md>)

Recorded evaluation configuration: {"Image Size":"128 x 352"}. This record does not assert independent reproduction.

### MT+PV

mIoU (Drivable Area): 48. Result ID: 699ebaa25698665ec489b7a7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d41e209131cea7f934.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64481e209131cea03b45.md>)

[Implementation](<https://github.com/CuriousAI/mean-teacher>)

Recorded evaluation configuration: {"Image Size":"128 x 352"}. This record does not assert independent reproduction.

### PCT\*

mIoU (Drivable Area): 47. Result ID: 699ebaa25698665ec489b7a6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d41e209131cea7f934.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ffaf.md>)

Recorded evaluation configuration: {"Image Size":"224 x 480"}. This record does not assert independent reproduction.

### DualCross

mIoU (Drivable Area): 45.7. Result ID: 699ebaa25698665ec489b7a4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d41e209131cea7f934.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73991e209131cea5d800.md>)

Recorded evaluation configuration: {"Image Size":"128 x 352"}. This record does not assert independent reproduction.

### Source Only

mIoU (Drivable Area): 44.7. Result ID: 699ebaa25698665ec489b7a3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d41e209131cea7f934.md>)

Recorded evaluation configuration: {"Image Size":"128 x 352"}. This record does not assert independent reproduction.

### DomainADV\*

mIoU (Drivable Area): 35.7. Result ID: 699ebaa25698665ec489b7a5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d41e209131cea7f934.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ffaf.md>)

Recorded evaluation configuration: {"Image Size":"224 x 480"}. This record does not assert independent reproduction.

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