# Glass panel segmentation on ST (test)

Source: [Glass panel segmentation on ST (test)](<https://www.sota2.com/research/sota/glass-panel-segmentation-on-st-test>)

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

Data updated: 2026-06-30T06:51:52.238Z

Evaluation of glass panel segmentation performance on the test split of the ST dataset, reporting metrics including Overall mIoU and various Coverage percentiles.

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 | Glass panel segmentation |
| Dataset (including any stated split) | ST (test) |
| Metric | Overall 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

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

- [Coverage 20% Percentile](<https://www.sota2.com/research/sota/glass-panel-segmentation-on-st-test.md?metric=Coverage%2020%25%20Percentile>): Higher is better; unit: PERCENT.

- [Coverage 10% Percentile](<https://www.sota2.com/research/sota/glass-panel-segmentation-on-st-test.md?metric=Coverage%2010%25%20Percentile>): Higher is better; unit: PERCENT.

- [Coverage 5% Percentile](<https://www.sota2.com/research/sota/glass-panel-segmentation-on-st-test.md?metric=Coverage%205%25%20Percentile>): Higher is better; unit: PERCENT.

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

## Recorded results

| Method | Overall mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| RefGlass-GS | 98.95 | Not recorded | 6a434d62ba73165dbb74376e |
| GhostingNet | 85.97 | Not recorded | 6a434d62ba73165dbb74376e |
| GlassSemNet | 80.2 | Not recorded | 6a434d62ba73165dbb74376e |
| EBLNet | 47.01 | Not recorded | 6a434d62ba73165dbb74376e |

### RefGlass-GS

Overall mIoU: 98.95. Result ID: 6a43676dfbc373592c92ef4f.

[Reporting paper](<https://www.sota2.com/research/paper/6a434d62ba73165dbb74376e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a434d62ba73165dbb74376e.md>)

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

### GhostingNet

Overall mIoU: 85.97. Result ID: 6a43676dfbc373592c92ef4d.

[Reporting paper](<https://www.sota2.com/research/paper/6a434d62ba73165dbb74376e.md>)

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

### GlassSemNet

Overall mIoU: 80.2. Result ID: 6a43676dfbc373592c92ef4e.

[Reporting paper](<https://www.sota2.com/research/paper/6a434d62ba73165dbb74376e.md>)

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

### EBLNet

Overall mIoU: 47.01. Result ID: 6a43676dfbc373592c92ef4c.

[Reporting paper](<https://www.sota2.com/research/paper/6a434d62ba73165dbb74376e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b691e209131cea2e313.md>)

[Implementation](<https://github.com/hehao13/EBLNet>)

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

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