# Semantic Segmentation on JM (test)

Source: [Semantic Segmentation on JM (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-jm-test>)

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

Data updated: 2026-03-24T17:27:27.618Z

Evaluation of Semantic Segmentation performance on the test split of the JM dataset, reporting overall mIoU and class-specific scores for Sand, Gravel, High veg, Low veg, Forest floor, and Water categories.

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 | Semantic Segmentation |
| Dataset (including any stated split) | JM (test) |
| Metric | mIoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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](<https://www.sota2.com/research/sota/semantic-segmentation-on-jm-test.md?metric=mIoU>): Higher is better; unit: PERCENT.

- [IoU (Sand)](<https://www.sota2.com/research/sota/semantic-segmentation-on-jm-test.md?metric=IoU%20(Sand)>): Higher is better; unit: PERCENT.

- [IoU (Gravel)](<https://www.sota2.com/research/sota/semantic-segmentation-on-jm-test.md?metric=IoU%20(Gravel)>): Higher is better; unit: PERCENT.

- [IoU (High veg)](<https://www.sota2.com/research/sota/semantic-segmentation-on-jm-test.md?metric=IoU%20(High%20veg)>): Higher is better; unit: PERCENT.

- [IoU (Low veg)](<https://www.sota2.com/research/sota/semantic-segmentation-on-jm-test.md?metric=IoU%20(Low%20veg)>): Higher is better; unit: PERCENT.

- [IoU (Forest floor)](<https://www.sota2.com/research/sota/semantic-segmentation-on-jm-test.md?metric=IoU%20(Forest%20floor)>): Higher is better; unit: PERCENT.

- [IoU (Water)](<https://www.sota2.com/research/sota/semantic-segmentation-on-jm-test.md?metric=IoU%20(Water)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| PTv2 | 95 | Not recorded | 69c21ad80636e5bf4afc4d9e |
| DGCNN | 74.4 | Not recorded | 69c21ad80636e5bf4afc4d9e |
| RF | 68.2 | Not recorded | 69c21ad80636e5bf4afc4d9e |
| RandLA-Net | 58 | Not recorded | 69c21ad80636e5bf4afc4d9e |

### PTv2

mIoU: 95. Result ID: 69c2c96547f34ce924aca27d.

[Reporting paper](<https://www.sota2.com/research/paper/69c21ad80636e5bf4afc4d9e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c21ad80636e5bf4afc4d9e.md>)

Recorded evaluation configuration: {"Features":"all features"}. This record does not assert independent reproduction.

### DGCNN

mIoU: 74.4. Result ID: 69c2c96547f34ce924aca27e.

[Reporting paper](<https://www.sota2.com/research/paper/69c21ad80636e5bf4afc4d9e.md>)

Recorded evaluation configuration: {"Features":"all features"}. This record does not assert independent reproduction.

### RF

mIoU: 68.2. Result ID: 69c2c96547f34ce924aca280.

[Reporting paper](<https://www.sota2.com/research/paper/69c21ad80636e5bf4afc4d9e.md>)

Recorded evaluation configuration: {"Number of decision trees":"500","Features":"all features and extra geometric features"}. This record does not assert independent reproduction.

### RandLA-Net

mIoU: 58. Result ID: 69c2c96547f34ce924aca27f.

[Reporting paper](<https://www.sota2.com/research/paper/69c21ad80636e5bf4afc4d9e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67771e209131cea16862.md>)

Recorded evaluation configuration: {"Features":"all features"}. This record does not assert independent reproduction.

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