# Semantic Segmentation on Pascal Object (val)

Source: [Semantic Segmentation on Pascal Object (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-object-val>)

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

Data updated: 2026-06-29T06:17:02.811Z

Evaluation of Semantic Segmentation performance on the validation split of the Pascal Object dataset, reporting metrics such as mIoU.

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) | Pascal Object (val) |
| 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-pascal-object-val.md?metric=mIoU>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| SynSeg | 36 | Not recorded | 68fa7a881e209131cea83ba7 |
| MGCCL | 33 | Not recorded | 68fa7a881e209131cea83ba7 |
| CoDe | 32.3 | Not recorded | 68fa7a881e209131cea83ba7 |
| TCL | 31.6 | Not recorded | 68fa7a881e209131cea83ba7 |
| S-Seg | 30.3 | Not recorded | 68fa7a881e209131cea83ba7 |
| GroupViT | 27.5 | Not recorded | 68fa7a881e209131cea83ba7 |
| OVSegmentor | 25.1 | Not recorded | 68fa7a881e209131cea83ba7 |
| ViewCo | 23.5 | Not recorded | 68fa7a881e209131cea83ba7 |
| CoCu | 22.7 | Not recorded | 68fa7a881e209131cea83ba7 |

### SynSeg

mIoU: 36. Result ID: 6a420dd8fbc373592c862b11.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a881e209131cea83ba7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a881e209131cea83ba7.md>)

Recorded evaluation configuration: {"Publication":"ICME 2026","Training Datasets":"CC12M"}. This record does not assert independent reproduction.

### MGCCL

mIoU: 33. Result ID: 6a420dd8fbc373592c862b10.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a881e209131cea83ba7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a881e209131cea83ba7.md>)

Recorded evaluation configuration: {"Publication":"TMC 2025","Training Datasets":"CC3M + CC12M"}. This record does not assert independent reproduction.

### CoDe

mIoU: 32.3. Result ID: 6a420dd8fbc373592c862b0e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a881e209131cea83ba7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d51e209131cea58cce.md>)

[Implementation](<https://github.com/072jiajia/image-text-co-decomposition>)

Recorded evaluation configuration: {"Publication":"CVPR 2024","Training Datasets":"CC3M+CC12M"}. This record does not assert independent reproduction.

### TCL

mIoU: 31.6. Result ID: 6a420dd8fbc373592c862b0d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a881e209131cea83ba7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42ce9.md>)

[Implementation](<https://github.com/kakaobrain/tcl>)

Recorded evaluation configuration: {"Publication":"CVPR 2023","Training Datasets":"CC3M+CC12M"}. This record does not assert independent reproduction.

### S-Seg

mIoU: 30.3. Result ID: 6a420dd8fbc373592c862b0f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a881e209131cea83ba7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71f91e209131cea53d93.md>)

Recorded evaluation configuration: {"Publication":"CVPR 2025","Training Datasets":"CC3M+CC12M"}. This record does not assert independent reproduction.

### GroupViT

mIoU: 27.5. Result ID: 6a420dd8fbc373592c862b09.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a881e209131cea83ba7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cfc1e209131cea371f1.md>)

[Implementation](<https://github.com/NVlabs/GroupViT>)

Recorded evaluation configuration: {"Publication":"CVPR 2022","Training Datasets":"CC3M+CC12M+RedCaps12M"}. This record does not assert independent reproduction.

### OVSegmentor

mIoU: 25.1. Result ID: 6a420dd8fbc373592c862b0c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a881e209131cea83ba7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eab1e209131cea4145b.md>)

[Implementation](<https://jazzcharles.github.io/OVSegmentor/>)

Recorded evaluation configuration: {"Publication":"CVPR 2023","Training Datasets":"CC12M"}. This record does not assert independent reproduction.

### ViewCo

mIoU: 23.5. Result ID: 6a420dd8fbc373592c862b0a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a881e209131cea83ba7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e991e209131cea40ff6.md>)

Recorded evaluation configuration: {"Publication":"ICLR 2023","Training Datasets":"CC12M+YFCC14M"}. This record does not assert independent reproduction.

### CoCu

mIoU: 22.7. Result ID: 6a420dd8fbc373592c862b0b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a881e209131cea83ba7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71ba1e209131cea52cec.md>)

Recorded evaluation configuration: {"Publication":"NeurIPS 2023","Training Datasets":"CC3M+CC12M+YFCC14M"}. This record does not assert independent reproduction.

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