# Semantic Segmentation on MUSES

Source: [Semantic Segmentation on MUSES](<https://www.sota2.com/research/sota/semantic-segmentation-on-muses>)

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

Data updated: 2026-02-26T06:04:11.580Z

Evaluation of Semantic Segmentation performance on the MUSES dataset, reporting metrics broken down by environmental conditions (Clear, Rain, Fog, Snow) and time of day (Day/Night).

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) | MUSES |
| Metric | Segmentation Accuracy (Clear, Day) |
| 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

- [Segmentation Accuracy (Clear, Day)](<https://www.sota2.com/research/sota/semantic-segmentation-on-muses.md?metric=Segmentation%20Accuracy%20(Clear%2C%20Day)>): Higher is better; unit: PERCENT.

- [Segmentation Accuracy (Clear, Night)](<https://www.sota2.com/research/sota/semantic-segmentation-on-muses.md?metric=Segmentation%20Accuracy%20(Clear%2C%20Night)>): Higher is better; unit: PERCENT.

- [Segmentation Accuracy (Rain, Day)](<https://www.sota2.com/research/sota/semantic-segmentation-on-muses.md?metric=Segmentation%20Accuracy%20(Rain%2C%20Day)>): Higher is better; unit: PERCENT.

- [Segmentation Accuracy (Rain, Night)](<https://www.sota2.com/research/sota/semantic-segmentation-on-muses.md?metric=Segmentation%20Accuracy%20(Rain%2C%20Night)>): Higher is better; unit: PERCENT.

- [Segmentation Accuracy (Fog, Day)](<https://www.sota2.com/research/sota/semantic-segmentation-on-muses.md?metric=Segmentation%20Accuracy%20(Fog%2C%20Day)>): Higher is better; unit: PERCENT.

- [Segmentation Accuracy (Fog, Night)](<https://www.sota2.com/research/sota/semantic-segmentation-on-muses.md?metric=Segmentation%20Accuracy%20(Fog%2C%20Night)>): Higher is better; unit: PERCENT.

- [Segmentation Accuracy (Snow, Day)](<https://www.sota2.com/research/sota/semantic-segmentation-on-muses.md?metric=Segmentation%20Accuracy%20(Snow%2C%20Day)>): Higher is better; unit: PERCENT.

- [Segmentation Accuracy (Snow, Night)](<https://www.sota2.com/research/sota/semantic-segmentation-on-muses.md?metric=Segmentation%20Accuracy%20(Snow%2C%20Night)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Segmentation Accuracy (Clear, Day) | Result date | Report paper |
| --- | --- | --- | --- |
| Oracles | 62.04 | Not recorded | 68fa779d1e209131cea745cf |
| SemLA | 60.98 | Not recorded | 68fa779d1e209131cea745cf |
| Uniform | 58.79 | Not recorded | 68fa779d1e209131cea745cf |
| Zero-shot | 38.05 | Not recorded | 68fa779d1e209131cea745cf |

### Oracles

Segmentation Accuracy (Clear, Day): 62.04. Result ID: 699553833badfaffe643a46b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa779d1e209131cea745cf.md>)

Recorded evaluation configuration: {"Backbone":"SED \[71\]","Oracle":"true"}. This record does not assert independent reproduction.

### SemLA

Segmentation Accuracy (Clear, Day): 60.98. Result ID: 699553833badfaffe643a46d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa779d1e209131cea745cf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa779d1e209131cea745cf.md>)

[Implementation](<https://thegoodailab.org/semla>)

Recorded evaluation configuration: {"Backbone":"SED \[71\]","tau":0.05,"K":5}. This record does not assert independent reproduction.

### Uniform

Segmentation Accuracy (Clear, Day): 58.79. Result ID: 699553833badfaffe643a46c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa779d1e209131cea745cf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74311e209131cea6054b.md>)

Recorded evaluation configuration: {"Backbone":"SED \[71\]","Merging":"Uniform"}. This record does not assert independent reproduction.

### Zero-shot

Segmentation Accuracy (Clear, Day): 38.05. Result ID: 699553833badfaffe643a46a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa779d1e209131cea745cf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b11e209131cea57ef4.md>)

[Implementation](<https://ku-cvlab.github.io/CAT-Seg/>)

Recorded evaluation configuration: {"Backbone":"SED \[71\]","Zero-shot":"true"}. This record does not assert independent reproduction.

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