# Referring Image Segmentation on refCOCO+ UMD (testA)

Source: [Referring Image Segmentation on refCOCO+ UMD (testA)](<https://www.sota2.com/research/sota/referring-image-segmentation-on-refcoco-plus-umd-testa>)

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

Data updated: 2026-02-26T06:10:36.366Z

Evaluation of Referring Image Segmentation performance on the testA split of the UMD version of the RefCOCO+ dataset, reporting IoU metrics.

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 | Referring Image Segmentation |
| Dataset (including any stated split) | refCOCO+ UMD (testA) |
| Metric | mIoU |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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/referring-image-segmentation-on-refcoco-plus-umd-testa.md?metric=mIoU>): Higher is better; unit: SCALAR.

## Recorded results

| Method | mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| VersaViT | 0.75 | Not recorded | 698c0d29c97a0b3e3b5e1223 |
| ReLA | 0.71 | Not recorded | 698c0d29c97a0b3e3b5e1223 |
| LAVT | 0.684 | Not recorded | 698c0d29c97a0b3e3b5e1223 |
| LISA-7B | 0.674 | Not recorded | 698c0d29c97a0b3e3b5e1223 |
| VISA-7B | 0.648 | Not recorded | 698c0d29c97a0b3e3b5e1223 |

### VersaViT

mIoU: 0.75. Result ID: 69971a875698665ec4686feb.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d29c97a0b3e3b5e1223.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698c0d29c97a0b3e3b5e1223.md>)

Recorded evaluation configuration: {"training":"Fine-tuning"}. This record does not assert independent reproduction.

### ReLA

mIoU: 0.71. Result ID: 69971a875698665ec4686fe8.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d29c97a0b3e3b5e1223.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f8e1e209131cea46367.md>)

[Implementation](<https://henghui.ding.github.io/GRES>)

Recorded evaluation configuration: {"training":"Fine-tuning"}. This record does not assert independent reproduction.

### LAVT

mIoU: 0.684. Result ID: 69971a875698665ec4686fe7.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d29c97a0b3e3b5e1223.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c2c1e209131cea328ba.md>)

[Implementation](<https://www.sota2.com/LAVT-RIS>)

Recorded evaluation configuration: {"training":"Fine-tuning"}. This record does not assert independent reproduction.

### LISA-7B

mIoU: 0.674. Result ID: 69971a875698665ec4686fe9.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d29c97a0b3e3b5e1223.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa730a1e209131cea5a0b2.md>)

[Implementation](<https://www.sota2.com/github.com/dvlab-research/LISA>)

Recorded evaluation configuration: {"training":"Fine-tuning","parameters":"7B"}. This record does not assert independent reproduction.

### VISA-7B

mIoU: 0.648. Result ID: 69971a875698665ec4686fea.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d29c97a0b3e3b5e1223.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa741f1e209131cea5fc43.md>)

[Implementation](<https://github.com/cilinyan/VISA>)

Recorded evaluation configuration: {"training":"Fine-tuning","parameters":"7B"}. This record does not assert independent reproduction.

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