# Semantic Segmentation on MARIDA

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

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

Data updated: 2026-02-26T05:51:33.157Z

Evaluation of Semantic Segmentation performance on the MARIDA dataset, reporting metrics including various Precision, Recall, F1 scores, Subset Accuracy, and IoU.

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) | MARIDA |
| Metric | Macro Precision |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

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

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

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

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

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

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

- [Macro F1](<https://www.sota2.com/research/sota/semantic-segmentation-on-marida.md?metric=Macro%20F1>): Higher is better; unit: PERCENT.

- [Micro F1](<https://www.sota2.com/research/sota/semantic-segmentation-on-marida.md?metric=Micro%20F1>): Higher is better; unit: PERCENT.

- [Weight F1](<https://www.sota2.com/research/sota/semantic-segmentation-on-marida.md?metric=Weight%20F1>): Higher is better; unit: PERCENT.

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

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

## Recorded results

| Method | Macro Precision | Result date | Report paper |
| --- | --- | --- | --- |
| UNet | 81 | Not recorded | 68fa6dad1e209131cea3b6cf |
| Residual Attention UNet | 81 | Not recorded | 68fa6dad1e209131cea3b6cf |
| Attention UNet | 78 | Not recorded | 68fa6dad1e209131cea3b6cf |
| UNet-MARIDA | 74 | Not recorded | 68fa6dad1e209131cea3b6cf |
| UNet | 69 | Not recorded | 68fa6dad1e209131cea3b6cf |
| UNet | 57 | Not recorded | 68fa6dad1e209131cea3b6cf |

### UNet

Macro Precision: 81. Result ID: 698fd4433a6c314849fc29ce.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dad1e209131cea3b6cf.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: {"Loss Function":"Xent"}. This record does not assert independent reproduction.

### Residual Attention UNet

Macro Precision: 81. Result ID: 698fd4433a6c314849fc29d2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dad1e209131cea3b6cf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dad1e209131cea3b6cf.md>)

[Implementation](<https://github.com/sheikhazhanmohammed/SADMA.git>)

Recorded evaluation configuration: {"Loss Function":"Xent"}. This record does not assert independent reproduction.

### Attention UNet

Macro Precision: 78. Result ID: 698fd4433a6c314849fc29d1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dad1e209131cea3b6cf.md>)

Recorded evaluation configuration: {"Loss Function":"Xent"}. This record does not assert independent reproduction.

### UNet-MARIDA

Macro Precision: 74. Result ID: 698fd4433a6c314849fc29cd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dad1e209131cea3b6cf.md>)

Recorded evaluation configuration: {"Loss Function":"Xent"}. This record does not assert independent reproduction.

### UNet

Macro Precision: 69. Result ID: 698fd4433a6c314849fc29d0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dad1e209131cea3b6cf.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: {"Loss Function":"Dice"}. This record does not assert independent reproduction.

### UNet

Macro Precision: 57. Result ID: 698fd4433a6c314849fc29cf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dad1e209131cea3b6cf.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: {"Loss Function":"Focal"}. This record does not assert independent reproduction.

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