# Semantic Segmentation on ImageNet curated subset (val)

Source: [Semantic Segmentation on ImageNet curated subset (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-imagenet-curated-subset-val>)

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

Data updated: 2026-04-23T11:03:02.847Z

Evaluation of Semantic Segmentation performance on a specific, curated subset of 4,276 images from the ImageNet validation set.

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) | ImageNet Segmentation curated subset of 4,276 images (val) |
| Metric | Pixel Accuracy |
| Unit | PERCENT |
| 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

- [Pixel Accuracy](<https://www.sota2.com/research/sota/semantic-segmentation-on-imagenet-curated-subset-val.md?metric=Pixel%20Accuracy>): Higher is better; unit: PERCENT.

- [mIoU](<https://www.sota2.com/research/sota/semantic-segmentation-on-imagenet-curated-subset-val.md?metric=mIoU>): Higher is better; unit: PERCENT.

- [mAP](<https://www.sota2.com/research/sota/semantic-segmentation-on-imagenet-curated-subset-val.md?metric=mAP>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Pixel Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CLIP-SVD | 77.55 | Not recorded | 68fa7b691e209131cea88420 |
| CLIP | 77.24 | Not recorded | 68fa7b691e209131cea88420 |

### CLIP-SVD

Pixel Accuracy: 77.55. Result ID: 69e9fc4947f34ce924d20d85.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b691e209131cea88420.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b691e209131cea88420.md>)

Recorded evaluation configuration: {"Framework":"TextSpan","Status":"fine-tuned"}. This record does not assert independent reproduction.

### CLIP

Pixel Accuracy: 77.24. Result ID: 69e9fc4947f34ce924d20d84.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b691e209131cea88420.md>)

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

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

Recorded evaluation configuration: {"Framework":"TextSpan","Status":"pre-trained"}. This record does not assert independent reproduction.

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