# Semantic Segmentation on X-Ray

Source: [Semantic Segmentation on X-Ray](<https://www.sota2.com/research/sota/semantic-segmentation-on-x-ray>)

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

Data updated: 2026-03-31T12:20:56.999Z

Evaluation of semantic segmentation performance on the X-Ray dataset, reporting mean Intersection over Union (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) | X-Ray |
| Metric | mIoU |
| 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](<https://www.sota2.com/research/sota/semantic-segmentation-on-x-ray.md?metric=mIoU>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| SegGPT | 89.1 | Not recorded | 69cb557f0636e5bf4afca3f2 |
| INSID3 | 80.1 | Not recorded | 69cb557f0636e5bf4afca3f2 |
| Matcher | 71.2 | Not recorded | 69cb557f0636e5bf4afca3f2 |
| GF-SAM† + our debias | 59.1 | Not recorded | 69cb557f0636e5bf4afca3f2 |
| GF-SAM† | 54.7 | Not recorded | 69cb557f0636e5bf4afca3f2 |
| GF-SAM | 52.9 | Not recorded | 69cb557f0636e5bf4afca3f2 |
| DiffewS | 45.1 | Not recorded | 69cb557f0636e5bf4afca3f2 |
| SINE | 40.6 | Not recorded | 69cb557f0636e5bf4afca3f2 |

### SegGPT

mIoU: 89.1. Result ID: 69cbbc2747f34ce924b54da9.

[Reporting paper](<https://www.sota2.com/research/paper/69cb557f0636e5bf4afca3f2.md>)

Recorded evaluation configuration: {"Encoder":"ViT","#Param":"354 M","Training Protocol":"Task-specific fine-tuning: Semantic + mask supervision","Shot count":"5"}. This record does not assert independent reproduction.

### INSID3

mIoU: 80.1. Result ID: 69cbbc2747f34ce924b54db0.

[Reporting paper](<https://www.sota2.com/research/paper/69cb557f0636e5bf4afca3f2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cb557f0636e5bf4afca3f2.md>)

[Implementation](<https://github.com/visinf/INSID3>)

Recorded evaluation configuration: {"Encoder":"DINOv3","#Param":"304 M","Training Protocol":"Training free: Unsupervised pre-training","Shot count":"5"}. This record does not assert independent reproduction.

### Matcher

mIoU: 71.2. Result ID: 69cbbc2747f34ce924b54dac.

[Reporting paper](<https://www.sota2.com/research/paper/69cb557f0636e5bf4afca3f2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71d71e209131cea534a4.md>)

[Implementation](<https://github.com/aim-uofa/Matcher>)

Recorded evaluation configuration: {"Encoder":"DINOv2 + SAM","#Param":"945 M","Training Protocol":"Training free: Mask-supervised pre-training","Shot count":"5"}. This record does not assert independent reproduction.

### GF-SAM† + our debias

mIoU: 59.1. Result ID: 69cbbc2747f34ce924b54daf.

[Reporting paper](<https://www.sota2.com/research/paper/69cb557f0636e5bf4afca3f2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75351e209131cea66694.md>)

[Implementation](<https://andyzaq.github.io/GF-SAM/>)

Recorded evaluation configuration: {"Encoder":"DINOv3 + SAM","#Param":"945 M","Training Protocol":"Training free: Mask-supervised pre-training","Shot count":"5"}. This record does not assert independent reproduction.

### GF-SAM†

mIoU: 54.7. Result ID: 69cbbc2747f34ce924b54dae.

[Reporting paper](<https://www.sota2.com/research/paper/69cb557f0636e5bf4afca3f2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75351e209131cea66694.md>)

[Implementation](<https://andyzaq.github.io/GF-SAM/>)

Recorded evaluation configuration: {"Encoder":"DINOv3 + SAM","#Param":"945 M","Training Protocol":"Training free: Mask-supervised pre-training","Shot count":"5"}. This record does not assert independent reproduction.

### GF-SAM

mIoU: 52.9. Result ID: 69cbbc2747f34ce924b54dad.

[Reporting paper](<https://www.sota2.com/research/paper/69cb557f0636e5bf4afca3f2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75351e209131cea66694.md>)

[Implementation](<https://andyzaq.github.io/GF-SAM/>)

Recorded evaluation configuration: {"Encoder":"DINOv2 + SAM","#Param":"945 M","Training Protocol":"Training free: Mask-supervised pre-training","Shot count":"5"}. This record does not assert independent reproduction.

### DiffewS

mIoU: 45.1. Result ID: 69cbbc2747f34ce924b54dab.

[Reporting paper](<https://www.sota2.com/research/paper/69cb557f0636e5bf4afca3f2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756b1e209131cea67c00.md>)

[Implementation](<https://github.com/aim-uofa/DiffewS>)

Recorded evaluation configuration: {"Encoder":"Stable Diffusion","#Param":"890 M","Training Protocol":"Task-specific fine-tuning: Semantic + mask supervision","Shot count":"5"}. This record does not assert independent reproduction.

### SINE

mIoU: 40.6. Result ID: 69cbbc2747f34ce924b54daa.

[Reporting paper](<https://www.sota2.com/research/paper/69cb557f0636e5bf4afca3f2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75211e209131cea66031.md>)

Recorded evaluation configuration: {"Encoder":"DINOv2","#Param":"373 M","Training Protocol":"Task-specific fine-tuning: Semantic + mask supervision","Shot count":"5"}. This record does not assert independent reproduction.

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