# Semantic Segmentation on ADE20K occluded (val)

Source: [Semantic Segmentation on ADE20K occluded (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-occluded-val>)

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

Data updated: 2026-06-01T08:37:25.798Z

Evaluation of Semantic Segmentation performance on the validation split of the ADE20K dataset under occluded conditions, typically measured by 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) | ADE20K occluded (val) |
| Metric | 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

- [mIoU](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-occluded-val.md?metric=mIoU>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| PRISM | 39.7 | Not recorded | 6a1d11e3dbd7150506f83dfc |
| PVTv2-B1 | 34.8 | Not recorded | 6a1d11e3dbd7150506f83dfc |
| XCiT-T12 | 32.2 | Not recorded | 6a1d11e3dbd7150506f83dfc |
| BiXT-Ti/16 | 30.5 | Not recorded | 6a1d11e3dbd7150506f83dfc |

### PRISM

mIoU: 39.7. Result ID: 6a1d44b3fbc373592c167d6c.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d11e3dbd7150506f83dfc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d11e3dbd7150506f83dfc.md>)

Recorded evaluation configuration: {"Param.":"15.5M","FLOPs":"35.6G"}. This record does not assert independent reproduction.

### PVTv2-B1

mIoU: 34.8. Result ID: 6a1d44b3fbc373592c167d6a.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d11e3dbd7150506f83dfc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f131e209131cea43b6a.md>)

[Implementation](<https://github.com/whai362/PVT>)

Recorded evaluation configuration: {"Param.":"17.8M","FLOPs":"34.2G"}. This record does not assert independent reproduction.

### XCiT-T12

mIoU: 32.2. Result ID: 6a1d44b3fbc373592c167d69.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d11e3dbd7150506f83dfc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a3f1e209131cea26fc7.md>)

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

Recorded evaluation configuration: {"Param.":"8M"}. This record does not assert independent reproduction.

### BiXT-Ti/16

mIoU: 30.5. Result ID: 6a1d44b3fbc373592c167d6b.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d11e3dbd7150506f83dfc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa757a1e209131cea683b8.md>)

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

Recorded evaluation configuration: {"Param.":"19M","FLOPs":"31.8G"}. This record does not assert independent reproduction.

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