# Semantic Segmentation on Poiqu Basin

Source: [Semantic Segmentation on Poiqu Basin](<https://www.sota2.com/research/sota/semantic-segmentation-on-poiqu-basin>)

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

Data updated: 2026-05-22T07:06:38.960Z

Evaluation of Semantic Segmentation performance on the Poiqu Basin dataset, reporting class-specific metrics (e.g., clean-ice glaciers, vegetation) and overall Mean Precision.

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) | Poiqu Basin |
| Metric | Precision (Clean-ice Glaciers) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Precision (Clean-ice Glaciers)](<https://www.sota2.com/research/sota/semantic-segmentation-on-poiqu-basin.md?metric=Precision%20(Clean-ice%20Glaciers)>): Higher is better; unit: PERCENT.

- [Precision (Debris-covered Glaciers)](<https://www.sota2.com/research/sota/semantic-segmentation-on-poiqu-basin.md?metric=Precision%20(Debris-covered%20Glaciers)>): Higher is better; unit: PERCENT.

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

- [Precision (Vegetation)](<https://www.sota2.com/research/sota/semantic-segmentation-on-poiqu-basin.md?metric=Precision%20(Vegetation)>): Higher is better; unit: PERCENT.

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

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

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

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

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

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

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

- [mIoU](<https://www.sota2.com/research/sota/semantic-segmentation-on-poiqu-basin.md?metric=mIoU>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Precision (Clean-ice Glaciers) | Result date | Report paper |
| --- | --- | --- | --- |
| CryoNet | 96.53 | Not recorded | 6a0fe2e1f984739ed6739b96 |
| SegFormer | 96.03 | Not recorded | 6a0fe2e1f984739ed6739b96 |
| U-Net | 94.46 | Not recorded | 6a0fe2e1f984739ed6739b96 |
| DeepLabV3+ | 94.02 | Not recorded | 6a0fe2e1f984739ed6739b96 |

### CryoNet

Precision (Clean-ice Glaciers): 96.53. Result ID: 6a10007dfbc373592c0872f4.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe2e1f984739ed6739b96.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0fe2e1f984739ed6739b96.md>)

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

### SegFormer

Precision (Clean-ice Glaciers): 96.03. Result ID: 6a10007dfbc373592c0872f6.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe2e1f984739ed6739b96.md>)

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

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

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

### U-Net

Precision (Clean-ice Glaciers): 94.46. Result ID: 6a10007dfbc373592c0872f7.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe2e1f984739ed6739b96.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61e11e209131ce9f653d.md>)

[Implementation](<http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net>)

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

### DeepLabV3+

Precision (Clean-ice Glaciers): 94.02. Result ID: 6a10007dfbc373592c0872f5.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe2e1f984739ed6739b96.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64b91e209131cea06121.md>)

[Implementation](<https://github.com/tensorflow/models/tree/master/research/deeplab>)

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.