# Semantic Segmentation on RescueNet (test)

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

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

Data updated: 2026-05-12T13:50:11.332Z

Evaluation of Semantic Segmentation performance on the test split of the RescueNet dataset, reporting class-specific metrics 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 | Semantic Segmentation |
| Dataset (including any stated split) | RescueNet (test) |
| Metric | Background IoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

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

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

- [Building Damage (None) IoU](<https://www.sota2.com/research/sota/semantic-segmentation-on-rescuenet-test.md?metric=Building%20Damage%20(None)%20IoU>): Higher is better; unit: PERCENT.

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

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

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

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

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

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

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

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

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

## Recorded results

| Method | Background IoU | Result date | Report paper |
| --- | --- | --- | --- |
| Mask2Former | 85.77 | Not recorded | 6a02b48edbc836b87d824cc5 |
| SegFormer-B4 | 85.7 | Not recorded | 6a02b48edbc836b87d824cc5 |
| DA-SegFormer | 85.02 | Not recorded | 6a02b48edbc836b87d824cc5 |

### Mask2Former

Background IoU: 85.77. Result ID: 6a03300f47f34ce924e7c8f6.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b48edbc836b87d824cc5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cbf1e209131cea35c19.md>)

[Implementation](<https://bowenc0221.github.io/mask2former>)

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

### SegFormer-B4

Background IoU: 85.7. Result ID: 6a03300f47f34ce924e7c8f7.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b48edbc836b87d824cc5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2d1e209131cea2c997.md>)

[Implementation](<https://www.sota2.com/github.com/NVlabs/SegFormer>)

Recorded evaluation configuration: {"inference\_protocol":"standard resizing"}. This record does not assert independent reproduction.

### DA-SegFormer

Background IoU: 85.02. Result ID: 6a03300f47f34ce924e7c8f8.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b48edbc836b87d824cc5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b48edbc836b87d824cc5.md>)

Recorded evaluation configuration: {"inference\_protocol":"1024x1024 sliding-window","OHEM":"true","Dice Loss":"true"}. This record does not assert independent reproduction.

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