# Semantic Segmentation on EXPo Drone-to-Vehicle target v1 (test)

Source: [Semantic Segmentation on EXPo Drone-to-Vehicle target v1 (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-expo-drone-to-vehicle-target-v1-test>)

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

Data updated: 2026-02-26T05:26:45.017Z

Evaluation of Semantic Segmentation performance on the test split of the EXPo Drone-to-Vehicle target v1 dataset, reporting overall metrics (Acc, mAcc, mIoU, fIoU) and per-class metrics for 11 categories including road, car, ground, and building.

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) | EXPo Drone-to-Vehicle target v1 (test) |
| Metric | Acc |
| 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

- [Acc](<https://www.sota2.com/research/sota/semantic-segmentation-on-expo-drone-to-vehicle-target-v1-test.md?metric=Acc>): Higher is better; unit: PERCENT.

- [mAcc](<https://www.sota2.com/research/sota/semantic-segmentation-on-expo-drone-to-vehicle-target-v1-test.md?metric=mAcc>): Higher is better; unit: PERCENT.

- [mIoU](<https://www.sota2.com/research/sota/semantic-segmentation-on-expo-drone-to-vehicle-target-v1-test.md?metric=mIoU>): Higher is better; unit: PERCENT.

- [fIoU](<https://www.sota2.com/research/sota/semantic-segmentation-on-expo-drone-to-vehicle-target-v1-test.md?metric=fIoU>): Higher is better; unit: PERCENT.

- [IoU (ground)](<https://www.sota2.com/research/sota/semantic-segmentation-on-expo-drone-to-vehicle-target-v1-test.md?metric=IoU%20(ground)>): Higher is better; unit: PERCENT.

- [IoU (building)](<https://www.sota2.com/research/sota/semantic-segmentation-on-expo-drone-to-vehicle-target-v1-test.md?metric=IoU%20(building)>): Higher is better; unit: PERCENT.

- [IoU (fence)](<https://www.sota2.com/research/sota/semantic-segmentation-on-expo-drone-to-vehicle-target-v1-test.md?metric=IoU%20(fence)>): Higher is better; unit: PERCENT.

- [IoU (person)](<https://www.sota2.com/research/sota/semantic-segmentation-on-expo-drone-to-vehicle-target-v1-test.md?metric=IoU%20(person)>): Higher is better; unit: PERCENT.

- [IoU (pole)](<https://www.sota2.com/research/sota/semantic-segmentation-on-expo-drone-to-vehicle-target-v1-test.md?metric=IoU%20(pole)>): Higher is better; unit: PERCENT.

- [IoU (road)](<https://www.sota2.com/research/sota/semantic-segmentation-on-expo-drone-to-vehicle-target-v1-test.md?metric=IoU%20(road)>): Higher is better; unit: PERCENT.

- [IoU (sidewalk)](<https://www.sota2.com/research/sota/semantic-segmentation-on-expo-drone-to-vehicle-target-v1-test.md?metric=IoU%20(sidewalk)>): Higher is better; unit: PERCENT.

- [IoU (veg)](<https://www.sota2.com/research/sota/semantic-segmentation-on-expo-drone-to-vehicle-target-v1-test.md?metric=IoU%20(veg)>): Higher is better; unit: PERCENT.

- [IoU (car)](<https://www.sota2.com/research/sota/semantic-segmentation-on-expo-drone-to-vehicle-target-v1-test.md?metric=IoU%20(car)>): Higher is better; unit: PERCENT.

- [IoU (wall)](<https://www.sota2.com/research/sota/semantic-segmentation-on-expo-drone-to-vehicle-target-v1-test.md?metric=IoU%20(wall)>): Higher is better; unit: PERCENT.

- [IoU (sign)](<https://www.sota2.com/research/sota/semantic-segmentation-on-expo-drone-to-vehicle-target-v1-test.md?metric=IoU%20(sign)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Acc | Result date | Report paper |
| --- | --- | --- | --- |
| Target | 86.12 | Not recorded | 68fa779f1e209131cea746f8 |
| EventFly | 75.5 | Not recorded | 68fa779f1e209131cea746f8 |
| MIC | 72.46 | Not recorded | 68fa779f1e209131cea746f8 |
| PLSR | 72.46 | Not recorded | 68fa779f1e209131cea746f8 |
| DACS | 71.78 | Not recorded | 68fa779f1e209131cea746f8 |
| AdaptSegNet | 68.29 | Not recorded | 68fa779f1e209131cea746f8 |
| Source-Only | 57.91 | Not recorded | 68fa779f1e209131cea746f8 |

### Target

Acc: 86.12. Result ID: 6995561f3badfaffe646aa7f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa779f1e209131cea746f8.md>)

Recorded evaluation configuration: {"adaptation\_mode":"supervised","training\_source":"vehicle ground truth"}. This record does not assert independent reproduction.

### EventFly

Acc: 75.5. Result ID: 6995561f3badfaffe646aa7e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa779f1e209131cea746f8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa779f1e209131cea746f8.md>)

[Implementation](<https://event-fly.github.io/>)

Recorded evaluation configuration: {"adaptation\_mode":"UDA","source":"drone","target":"vehicle"}. This record does not assert independent reproduction.

### MIC

Acc: 72.46. Result ID: 6995561f3badfaffe646aa7c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa779f1e209131cea746f8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee41e209131cea42b0d.md>)

[Implementation](<https://github.com/lhoyer/MIC>)

Recorded evaluation configuration: {"adaptation\_mode":"UDA","source":"drone","target":"vehicle"}. This record does not assert independent reproduction.

### PLSR

Acc: 72.46. Result ID: 6995561f3badfaffe646aa7d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa779f1e209131cea746f8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71ab1e209131cea5273d.md>)

Recorded evaluation configuration: {"adaptation\_mode":"UDA","source":"drone","target":"vehicle"}. This record does not assert independent reproduction.

### DACS

Acc: 71.78. Result ID: 6995561f3badfaffe646aa7b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa779f1e209131cea746f8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68d91e209131cea1eaa7.md>)

[Implementation](<https://github.com/vikolss/DACS>)

Recorded evaluation configuration: {"adaptation\_mode":"UDA","source":"drone","target":"vehicle"}. This record does not assert independent reproduction.

### AdaptSegNet

Acc: 68.29. Result ID: 6995561f3badfaffe646aa7a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa779f1e209131cea746f8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67eb1e209131cea19203.md>)

[Implementation](<https://github.com/wasidennis/AdaptSegNet>)

Recorded evaluation configuration: {"adaptation\_mode":"UDA","source":"drone","target":"vehicle"}. This record does not assert independent reproduction.

### Source-Only

Acc: 57.91. Result ID: 6995561f3badfaffe646aa79.

[Reporting paper](<https://www.sota2.com/research/paper/68fa779f1e209131cea746f8.md>)

Recorded evaluation configuration: {"adaptation\_mode":"none","training\_source":"drone"}. This record does not assert independent reproduction.

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