# Semantic Segmentation on ADE20K-C level 4 (val)

Source: [Semantic Segmentation on ADE20K-C level 4 (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-c-level-4-val>)

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

Data updated: 2026-02-26T06:04:04.863Z

Evaluation of Semantic Segmentation performance on the ADE20K validation set under various image corruptions (e.g., brightness, fog, noise) at severity level 4.

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-C level 4 (val) |
| Metric | Score (Brightness) |
| 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

- [Score (Brightness)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-c-level-4-val.md?metric=Score%20(Brightness)>): Higher is better; unit: PERCENT.

- [Score (Contrast)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-c-level-4-val.md?metric=Score%20(Contrast)>): Higher is better; unit: PERCENT.

- [Score (Defocus)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-c-level-4-val.md?metric=Score%20(Defocus)>): Higher is better; unit: PERCENT.

- [Score (Elastic)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-c-level-4-val.md?metric=Score%20(Elastic)>): Higher is better; unit: PERCENT.

- [Score (Fog)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-c-level-4-val.md?metric=Score%20(Fog)>): Higher is better; unit: PERCENT.

- [Score (Frost)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-c-level-4-val.md?metric=Score%20(Frost)>): Higher is better; unit: PERCENT.

- [Score (Gaussian Noise)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-c-level-4-val.md?metric=Score%20(Gaussian%20Noise)>): Higher is better; unit: PERCENT.

- [Score (Glass Blur)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-c-level-4-val.md?metric=Score%20(Glass%20Blur)>): Higher is better; unit: PERCENT.

- [Score (Impulse Noise)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-c-level-4-val.md?metric=Score%20(Impulse%20Noise)>): Higher is better; unit: PERCENT.

- [Score (JPEG)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-c-level-4-val.md?metric=Score%20(JPEG)>): Higher is better; unit: PERCENT.

- [Score (Motion Blur)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-c-level-4-val.md?metric=Score%20(Motion%20Blur)>): Higher is better; unit: PERCENT.

- [Score (Pixelate)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-c-level-4-val.md?metric=Score%20(Pixelate)>): Higher is better; unit: PERCENT.

- [Score (Shot Noise)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-c-level-4-val.md?metric=Score%20(Shot%20Noise)>): Higher is better; unit: PERCENT.

- [Score (Snow)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-c-level-4-val.md?metric=Score%20(Snow)>): Higher is better; unit: PERCENT.

- [Score (Zoom Blur)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-c-level-4-val.md?metric=Score%20(Zoom%20Blur)>): Higher is better; unit: PERCENT.

- [Avg Score](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-c-level-4-val.md?metric=Avg%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Score (Brightness) | Result date | Report paper |
| --- | --- | --- | --- |
| VICT | 44.4 | Not recorded | 68fa779d1e209131cea745cd |
| Painter | 44.1 | Not recorded | 68fa779d1e209131cea745cd |
| VICT | 44 | Not recorded | 68fa779d1e209131cea745cd |
| Painter | 43.4 | Not recorded | 68fa779d1e209131cea745cd |

### VICT

Score (Brightness): 44.4. Result ID: 699553463badfaffe643613a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa779d1e209131cea745cd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa779d1e209131cea745cd.md>)

[Implementation](<https://github.com/Jiahao000/VICT>)

Recorded evaluation configuration: {"Setting":"one-shot"}. This record does not assert independent reproduction.

### Painter

Score (Brightness): 44.1. Result ID: 699553463badfaffe6436139.

[Reporting paper](<https://www.sota2.com/research/paper/68fa779d1e209131cea745cd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee51e209131cea42b1f.md>)

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

Recorded evaluation configuration: {"Setting":"one-shot"}. This record does not assert independent reproduction.

### VICT

Score (Brightness): 44. Result ID: 699553463badfaffe6436138.

[Reporting paper](<https://www.sota2.com/research/paper/68fa779d1e209131cea745cd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa779d1e209131cea745cd.md>)

[Implementation](<https://github.com/Jiahao000/VICT>)

Recorded evaluation configuration: {"Setting":"zero-shot"}. This record does not assert independent reproduction.

### Painter

Score (Brightness): 43.4. Result ID: 699553463badfaffe6436137.

[Reporting paper](<https://www.sota2.com/research/paper/68fa779d1e209131cea745cd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee51e209131cea42b1f.md>)

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

Recorded evaluation configuration: {"Setting":"zero-shot"}. This record does not assert independent reproduction.

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