# Keyhole Segmentation on L-PBF keyhole dataset (worst performing samples)

Source: [Keyhole Segmentation on L-PBF keyhole dataset (worst performing samples)](<https://www.sota2.com/research/sota/keyhole-segmentation-on-l-pbf-keyhole-dataset-worst-performing-samples>)

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

Data updated: 2026-06-16T09:36:44.944Z

Evaluation of Keyhole Segmentation performance on the worst performing samples subset of the L-PBF keyhole dataset, reporting IoU, F1, Precision, and Accuracy.

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 | Keyhole Segmentation |
| Dataset (including any stated split) | L-PBF keyhole dataset (worst performing samples) |
| Metric | mIoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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/keyhole-segmentation-on-l-pbf-keyhole-dataset-worst-performing-samples.md?metric=mIoU>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/keyhole-segmentation-on-l-pbf-keyhole-dataset-worst-performing-samples.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/keyhole-segmentation-on-l-pbf-keyhole-dataset-worst-performing-samples.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Accuracy](<https://www.sota2.com/research/sota/keyhole-segmentation-on-l-pbf-keyhole-dataset-worst-performing-samples.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| MOSAIC | 73.8 | Not recorded | 6a30d900d33dfb23e783d14a |
| SAM 2.1 | 73.5 | Not recorded | 6a30d900d33dfb23e783d14a |
| YOLO | 71.2 | Not recorded | 6a30d900d33dfb23e783d14a |
| SAM 2.1 | 66.3 | Not recorded | 6a30d900d33dfb23e783d14a |
| YOLO | 44.2 | Not recorded | 6a30d900d33dfb23e783d14a |

### MOSAIC

mIoU: 73.8. Result ID: 6a311918fbc373592c2dcfc9.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d900d33dfb23e783d14a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a30d900d33dfb23e783d14a.md>)

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

### SAM 2.1

mIoU: 73.5. Result ID: 6a311918fbc373592c2dcfcc.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d900d33dfb23e783d14a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e54.md>)

[Implementation](<https://github.com/facebookresearch/sam2>)

Recorded evaluation configuration: {"Prompting mode":"manual"}. This record does not assert independent reproduction.

### YOLO

mIoU: 71.2. Result ID: 6a311918fbc373592c2dcfca.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d900d33dfb23e783d14a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a21068ec10484bac23f014a.md>)

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

Recorded evaluation configuration: {"Evaluation split":"training"}. This record does not assert independent reproduction.

### SAM 2.1

mIoU: 66.3. Result ID: 6a311918fbc373592c2dcfcd.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d900d33dfb23e783d14a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e54.md>)

[Implementation](<https://github.com/facebookresearch/sam2>)

Recorded evaluation configuration: {"Prompting mode":"auto"}. This record does not assert independent reproduction.

### YOLO

mIoU: 44.2. Result ID: 6a311918fbc373592c2dcfcb.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d900d33dfb23e783d14a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a21068ec10484bac23f014a.md>)

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

Recorded evaluation configuration: {"Evaluation split":"testing"}. This record does not assert independent reproduction.

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