# Semantic Segmentation on Indoor Categories (in-domain)

Source: [Semantic Segmentation on Indoor Categories (in-domain)](<https://www.sota2.com/research/sota/semantic-segmentation-on-indoor-categories-in-domain>)

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

Data updated: 2026-02-26T05:37:42.910Z

Evaluation of Semantic Segmentation performance on the 'Indoor Categories (in-domain)' subset, reporting class-specific Accuracy and mIoU for categories including Bed, Pillow, Lamp, Window, and Painting.

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) | Semantic Segmentation Indoor Categories (in-domain) |
| Metric | Bed Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Bed Accuracy](<https://www.sota2.com/research/sota/semantic-segmentation-on-indoor-categories-in-domain.md?metric=Bed%20Accuracy>): Higher is better; unit: PERCENT.

- [Bed mIoU](<https://www.sota2.com/research/sota/semantic-segmentation-on-indoor-categories-in-domain.md?metric=Bed%20mIoU>): Higher is better; unit: PERCENT.

- [Pillow Accuracy](<https://www.sota2.com/research/sota/semantic-segmentation-on-indoor-categories-in-domain.md?metric=Pillow%20Accuracy>): Higher is better; unit: PERCENT.

- [Pillow mIoU](<https://www.sota2.com/research/sota/semantic-segmentation-on-indoor-categories-in-domain.md?metric=Pillow%20mIoU>): Higher is better; unit: PERCENT.

- [Lamp Accuracy](<https://www.sota2.com/research/sota/semantic-segmentation-on-indoor-categories-in-domain.md?metric=Lamp%20Accuracy>): Higher is better; unit: PERCENT.

- [Lamp mIoU](<https://www.sota2.com/research/sota/semantic-segmentation-on-indoor-categories-in-domain.md?metric=Lamp%20mIoU>): Higher is better; unit: PERCENT.

- [Window Accuracy](<https://www.sota2.com/research/sota/semantic-segmentation-on-indoor-categories-in-domain.md?metric=Window%20Accuracy>): Higher is better; unit: PERCENT.

- [Window mIoU](<https://www.sota2.com/research/sota/semantic-segmentation-on-indoor-categories-in-domain.md?metric=Window%20mIoU>): Higher is better; unit: PERCENT.

- [Painting Accuracy](<https://www.sota2.com/research/sota/semantic-segmentation-on-indoor-categories-in-domain.md?metric=Painting%20Accuracy>): Higher is better; unit: PERCENT.

- [Painting mIoU](<https://www.sota2.com/research/sota/semantic-segmentation-on-indoor-categories-in-domain.md?metric=Painting%20mIoU>): Higher is better; unit: PERCENT.

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

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

## Recorded results

| Method | Bed Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DMP | 89.47 | Not recorded | 68fa72ba1e209131cea5830d |
| ControlNet | 52.15 | Not recorded | 68fa72ba1e209131cea5830d |
| Palette | 3.47 | Not recorded | 68fa72ba1e209131cea5830d |

### DMP

Bed Accuracy: 89.47. Result ID: 6992567a3a6c3148490e46ae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea5830d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea5830d.md>)

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

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

### ControlNet

Bed Accuracy: 52.15. Result ID: 6992567a3a6c3148490e46ac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea5830d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71481e209131cea50695.md>)

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

### Palette

Bed Accuracy: 3.47. Result ID: 6992567a3a6c3148490e46ad.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea5830d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c7e1e209131cea3452f.md>)

[Implementation](<https://diffusion-palette.github.io/>)

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.