# Semantic Segmentation on ADE20k 100-5 (11 steps) overlapped

Source: [Semantic Segmentation on ADE20k 100-5 (11 steps) overlapped](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-100-5-11-steps-overlapped>)

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

Data updated: 2026-02-26T06:10:53.196Z

Evaluation of Semantic Segmentation performance on the ADE20K dataset using the specific '100-5 (11 steps) overlapped' class configuration, measured by mIoU across specified class ranges (1-100, 101-150, and All).

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 100-5 (11 steps) overlapped |
| Metric | mIoU (1-100) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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 (1-100)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-100-5-11-steps-overlapped.md?metric=mIoU%20(1-100)>): Higher is better; unit: PERCENT.

- [mIoU (101-150)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-100-5-11-steps-overlapped.md?metric=mIoU%20(101-150)>): Higher is better; unit: PERCENT.

- [mIoU (All)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-100-5-11-steps-overlapped.md?metric=mIoU%20(All)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU (1-100) | Result date | Report paper |
| --- | --- | --- | --- |
| Joint | 50.1 | Not recorded | 68fa74201e209131cea5fcdf |
| MBS | 48 | Not recorded | 68fa74201e209131cea5fcdf |
| INC | 46.9 | Not recorded | 68fa74201e209131cea5fcdf |
| Joint | 43.9 | Not recorded | 68fa74201e209131cea5fcdf |
| MiB | 40.2 | Not recorded | 68fa74201e209131cea5fcdf |
| PLOP | 39.1 | Not recorded | 68fa74201e209131cea5fcdf |
| RCIL | 38.5 | Not recorded | 68fa74201e209131cea5fcdf |
| MiB | 36 | Not recorded | 68fa74201e209131cea5fcdf |

### Joint

mIoU (1-100): 50.1. Result ID: 69931e973a6c31484913d9f5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fcdf.md>)

Recorded evaluation configuration: {"Backbone Type":"Transformer-based"}. This record does not assert independent reproduction.

### MBS

mIoU (1-100): 48. Result ID: 69931e973a6c31484913d9f4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fcdf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fcdf.md>)

[Implementation](<https://github.com/RoadoneP/ECCV2024_MBS>)

Recorded evaluation configuration: {"Backbone Type":"Transformer-based"}. This record does not assert independent reproduction.

### INC

mIoU (1-100): 46.9. Result ID: 69931e973a6c31484913d9f3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fcdf.md>)

Recorded evaluation configuration: {"Backbone Type":"Transformer-based"}. This record does not assert independent reproduction.

### Joint

mIoU (1-100): 43.9. Result ID: 69931e973a6c31484913d9f1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fcdf.md>)

Recorded evaluation configuration: {"Backbone Type":"CNN-based"}. This record does not assert independent reproduction.

### MiB

mIoU (1-100): 40.2. Result ID: 69931e973a6c31484913d9f2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fcdf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa673c1e209131cea1516c.md>)

[Implementation](<https://github.com/fcdl94/MiB>)

Recorded evaluation configuration: {"Backbone Type":"Transformer-based"}. This record does not assert independent reproduction.

### PLOP

mIoU (1-100): 39.1. Result ID: 69931e973a6c31484913d9ef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fcdf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697f1e209131cea22779.md>)

[Implementation](<https://github.com/arthurdouillard/CVPR2021_PLOP>)

Recorded evaluation configuration: {"Backbone Type":"CNN-based"}. This record does not assert independent reproduction.

### RCIL

mIoU (1-100): 38.5. Result ID: 69931e973a6c31484913d9f0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fcdf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bfd1e209131cea31762.md>)

[Implementation](<https://github.com/zhangchbin/RCIL>)

Recorded evaluation configuration: {"Backbone Type":"CNN-based"}. This record does not assert independent reproduction.

### MiB

mIoU (1-100): 36. Result ID: 69931e973a6c31484913d9ee.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74201e209131cea5fcdf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa673c1e209131cea1516c.md>)

[Implementation](<https://github.com/fcdl94/MiB>)

Recorded evaluation configuration: {"Backbone Type":"CNN-based"}. This record does not assert independent reproduction.

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