# Inference Speed (FPS) on Semantic Segmentation on COCO (val)

Source: [Inference Speed (FPS) on Semantic Segmentation on COCO (val)](<https://www.sota2.com/research/sota/inference-speed-fps-on-semantic-segmentation-on-coco-val>)

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

Data updated: 2026-02-26T05:44:57.915Z

Evaluation focusing on inference speed (Frames Per Second) for Semantic Segmentation models on the validation split of the COCO dataset.

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) | COCO (val) |
| Metric | FPS |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [FPS](<https://www.sota2.com/research/sota/inference-speed-fps-on-semantic-segmentation-on-coco-val.md?metric=FPS>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FPS | Result date | Report paper |
| --- | --- | --- | --- |
| FC-CLIP | 2.76 | Not recorded | 68fa71291e209131cea4f931 |
| ODISE | 0.39 | Not recorded | 68fa71291e209131cea4f931 |

### FC-CLIP

FPS: 2.76. Result ID: 69919f853a6c314849097427.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71291e209131cea4f931.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71291e209131cea4f931.md>)

[Implementation](<https://github.com/bytedance/fc-clip>)

Recorded evaluation configuration: {"GPU":"one V100 GPU","CUDA version":"11.6","PyTorch version":"1.13","Post-processing":"included"}. This record does not assert independent reproduction.

### ODISE

FPS: 0.39. Result ID: 69919f853a6c314849097426.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71291e209131cea4f931.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f081e209131cea4371a.md>)

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

Recorded evaluation configuration: {"GPU":"one V100 GPU","CUDA version":"11.6","PyTorch version":"1.13","Post-processing":"included"}. This record does not assert independent reproduction.

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