# Semantic Segmentation on FoodSeg103 1.0 (test)

Source: [Semantic Segmentation on FoodSeg103 1.0 (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-foodseg103-1-0-test>)

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

Data updated: 2026-02-26T06:10:13.238Z

Evaluation of Semantic Segmentation performance on the test split of the FoodSeg103 1.0 dataset, reporting Mean Intersection over Union (mIoU) and Mean Accuracy (mAcc).

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) | FoodSeg103 1.0 (test) |
| Metric | mIoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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-foodseg103-1-0-test.md?metric=mIoU>): Higher is better; unit: PERCENT.

- [mAcc](<https://www.sota2.com/research/sota/semantic-segmentation-on-foodseg103-1-0-test.md?metric=mAcc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| ReLeM-SeTR | 43.9 | Not recorded | 68fa69f01e209131cea25165 |
| ReLeM-SeTR | 43.2 | Not recorded | 68fa69f01e209131cea25165 |
| SeTR | 41.3 | Not recorded | 68fa69f01e209131cea25165 |
| ReLeM-CCNet | 36.8 | Not recorded | 68fa69f01e209131cea25165 |
| ReLeM-CCNet | 36 | Not recorded | 68fa69f01e209131cea25165 |
| CCNet | 35.5 | Not recorded | 68fa69f01e209131cea25165 |
| ReLeM-FPN | 29.1 | Not recorded | 68fa69f01e209131cea25165 |
| ReLeM-FPN | 28.9 | Not recorded | 68fa69f01e209131cea25165 |
| FPN | 27.8 | Not recorded | 68fa69f01e209131cea25165 |

### ReLeM-SeTR

mIoU: 43.9. Result ID: 698df7c3ffc3901de099d1ff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69f01e209131cea25165.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69f01e209131cea25165.md>)

[Implementation](<https://xiongweiwu.github.io/foodseg103.html>)

Recorded evaluation configuration: {"ReLeM Variant":"LSTM","Backbone":"ViT-16/B","Model Size":"723M"}. This record does not assert independent reproduction.

### ReLeM-SeTR

mIoU: 43.2. Result ID: 698df7c3ffc3901de099d200.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69f01e209131cea25165.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69f01e209131cea25165.md>)

[Implementation](<https://xiongweiwu.github.io/foodseg103.html>)

Recorded evaluation configuration: {"ReLeM Variant":"Transformer","Backbone":"ViT-16/B","Model Size":"723M"}. This record does not assert independent reproduction.

### SeTR

mIoU: 41.3. Result ID: 698df7c3ffc3901de099d1fe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69f01e209131cea25165.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a751e209131cea28425.md>)

[Implementation](<https://fudan-zvg.github.io/SETR>)

Recorded evaluation configuration: {"Backbone":"ViT-16/B","Model Size":"723M"}. This record does not assert independent reproduction.

### ReLeM-CCNet

mIoU: 36.8. Result ID: 698df7c3ffc3901de099d1f9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69f01e209131cea25165.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69f01e209131cea25165.md>)

[Implementation](<https://xiongweiwu.github.io/foodseg103.html>)

Recorded evaluation configuration: {"ReLeM Variant":"LSTM","Backbone":"ResNet-50","Model Size":"381M"}. This record does not assert independent reproduction.

### ReLeM-CCNet

mIoU: 36. Result ID: 698df7c3ffc3901de099d1fa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69f01e209131cea25165.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69f01e209131cea25165.md>)

[Implementation](<https://xiongweiwu.github.io/foodseg103.html>)

Recorded evaluation configuration: {"ReLeM Variant":"Transformer","Backbone":"ResNet-50","Model Size":"381M"}. This record does not assert independent reproduction.

### CCNet

mIoU: 35.5. Result ID: 698df7c3ffc3901de099d1f8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69f01e209131cea25165.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67ef1e209131cea193bd.md>)

[Implementation](<https://github.com/speedinghzl/CCNet>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Model Size":"381M"}. This record does not assert independent reproduction.

### ReLeM-FPN

mIoU: 29.1. Result ID: 698df7c3ffc3901de099d1fc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69f01e209131cea25165.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69f01e209131cea25165.md>)

[Implementation](<https://xiongweiwu.github.io/foodseg103.html>)

Recorded evaluation configuration: {"ReLeM Variant":"LSTM","Backbone":"ResNet-50","Model Size":"218M"}. This record does not assert independent reproduction.

### ReLeM-FPN

mIoU: 28.9. Result ID: 698df7c3ffc3901de099d1fd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69f01e209131cea25165.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69f01e209131cea25165.md>)

[Implementation](<https://xiongweiwu.github.io/foodseg103.html>)

Recorded evaluation configuration: {"ReLeM Variant":"Transformer","Backbone":"ResNet-50","Model Size":"218M"}. This record does not assert independent reproduction.

### FPN

mIoU: 27.8. Result ID: 698df7c3ffc3901de099d1fb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69f01e209131cea25165.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65a41e209131cea0b8b3.md>)

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

Recorded evaluation configuration: {"Backbone":"ResNet-50","Model Size":"218M"}. This record does not assert independent reproduction.

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