# Open-vocabulary Semantic Segmentation on Aggregate VOC, Context, ADE, Cityscapes, COCO Stuff

Source: [Open-vocabulary Semantic Segmentation on Aggregate VOC, Context, ADE, Cityscapes, COCO Stuff](<https://www.sota2.com/research/sota/open-vocabulary-semantic-segmentation-on-aggregate-voc-context-ade-cityscapes-coco-stuff>)

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

Data updated: 2026-05-12T08:10:31.023Z

Evaluation of Open-vocabulary Semantic Segmentation performance across an aggregate benchmark combining VOC, Context, ADE, Cityscapes, and COCO Stuff datasets, measured by Avg. 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 | Open-vocabulary Semantic Segmentation |
| Dataset (including any stated split) | Aggregate VOC, Context, ADE, Cityscapes, COCO Stuff |
| Metric | Average mIoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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

- [Average mIoU](<https://www.sota2.com/research/sota/open-vocabulary-semantic-segmentation-on-aggregate-voc-context-ade-cityscapes-coco-stuff.md?metric=Average%20mIoU>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Average mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| +CS & AMF (GCLIP) | 39 | Not recorded | 68fa77a51e209131cea74976 |
| +CS | 38 | Not recorded | 68fa77a51e209131cea74976 |
| ClearCLIP | 37.5 | Not recorded | 68fa77a51e209131cea74976 |
| GEM‡ | 37.2 | Not recorded | 68fa77a51e209131cea74976 |
| SCLIP | 37.1 | Not recorded | 68fa77a51e209131cea74976 |
| TCL | 33.1 | Not recorded | 68fa77a51e209131cea74976 |
| ReCLIP | 32.8 | Not recorded | 68fa77a51e209131cea74976 |
| MaskCLIP+† | 31.6 | Not recorded | 68fa77a51e209131cea74976 |
| GroupViT‡ | 27.7 | Not recorded | 68fa77a51e209131cea74976 |
| MaskCLIP† | 22.8 | Not recorded | 68fa77a51e209131cea74976 |
| CLIP‡ | 12.6 | Not recorded | 68fa77a51e209131cea74976 |

### +CS & AMF (GCLIP)

Average mIoU: 39. Result ID: 6a02df5e47f34ce924e58064.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a51e209131cea74976.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a51e209131cea74976.md>)

Recorded evaluation configuration: {"Pub. & Year":"Ours","Setting":"TF-OVSS"}. This record does not assert independent reproduction.

### +CS

Average mIoU: 38. Result ID: 6a02df5e47f34ce924e58063.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a51e209131cea74976.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a51e209131cea74976.md>)

Recorded evaluation configuration: {"Pub. & Year":"Ours","Setting":"TF-OVSS"}. This record does not assert independent reproduction.

### ClearCLIP

Average mIoU: 37.5. Result ID: 6a02df5e47f34ce924e58062.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a51e209131cea74976.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74231e209131cea5fe92.md>)

Recorded evaluation configuration: {"Pub. & Year":"ECCV’24","Setting":"TF-OVSS"}. This record does not assert independent reproduction.

### GEM‡

Average mIoU: 37.2. Result ID: 6a02df5e47f34ce924e58060.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a51e209131cea74976.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71711e209131cea51429.md>)

[Implementation](<https://github.com/WalBouss/GEM>)

Recorded evaluation configuration: {"Pub. & Year":"CVPR’24","Setting":"TF-OVSS"}. This record does not assert independent reproduction.

### SCLIP

Average mIoU: 37.1. Result ID: 6a02df5e47f34ce924e58061.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a51e209131cea74976.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756e1e209131cea67d7c.md>)

Recorded evaluation configuration: {"Pub. & Year":"ECCV’24","Setting":"TF-OVSS"}. This record does not assert independent reproduction.

### TCL

Average mIoU: 33.1. Result ID: 6a02df5e47f34ce924e5805b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a51e209131cea74976.md>)

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

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

Recorded evaluation configuration: {"Pub. & Year":"CVPR’23","Setting":"T-OVSS"}. This record does not assert independent reproduction.

### ReCLIP

Average mIoU: 32.8. Result ID: 6a02df5e47f34ce924e5805d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a51e209131cea74976.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7af91e209131cea860e7.md>)

[Implementation](<https://github.com/dogehhh/ReCLIP>)

Recorded evaluation configuration: {"Pub. & Year":"CVPR’24","Setting":"USS"}. This record does not assert independent reproduction.

### MaskCLIP+†

Average mIoU: 31.6. Result ID: 6a02df5e47f34ce924e5805c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a51e209131cea74976.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d1f1e209131cea37ece.md>)

Recorded evaluation configuration: {"Pub. & Year":"ECCV’22","Setting":"USS"}. This record does not assert independent reproduction.

### GroupViT‡

Average mIoU: 27.7. Result ID: 6a02df5e47f34ce924e5805a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a51e209131cea74976.md>)

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

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

Recorded evaluation configuration: {"Pub. & Year":"CVPR’22","Setting":"T-OVSS"}. This record does not assert independent reproduction.

### MaskCLIP†

Average mIoU: 22.8. Result ID: 6a02df5e47f34ce924e5805f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a51e209131cea74976.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d1f1e209131cea37ece.md>)

Recorded evaluation configuration: {"Pub. & Year":"ECCV’22","Setting":"TF-OVSS"}. This record does not assert independent reproduction.

### CLIP‡

Average mIoU: 12.6. Result ID: 6a02df5e47f34ce924e5805e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77a51e209131cea74976.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"Pub. & Year":"ICML’21","Setting":"TF-OVSS"}. This record does not assert independent reproduction.

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