# Visual Grounding on RefCOCO and LISA Combined

Source: [Visual Grounding on RefCOCO and LISA Combined](<https://www.sota2.com/research/sota/visual-grounding-on-refcoco-and-lisa-combined>)

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

Data updated: 2026-03-25T13:46:35.906Z

Evaluation of Visual Grounding performance on a combined dataset consisting of RefCOCO and LISA.

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 | Visual Grounding |
| Dataset (including any stated split) | RefCOCO and LISA Combined |
| Metric | Average IoU@50 |
| Unit | PERCENT |
| 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

- [Average IoU@50](<https://www.sota2.com/research/sota/visual-grounding-on-refcoco-and-lisa-combined.md?metric=Average%20IoU%4050>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Average IoU@50 | Result date | Report paper |
| --- | --- | --- | --- |
| PEPOG | 83.46 | Not recorded | 69c36c3b0636e5bf4afc662b |
| PEPOD | 83.1 | Not recorded | 69c36c3b0636e5bf4afc662b |
| GRPO | 82.6 | Not recorded | 69c36c3b0636e5bf4afc662b |
| DAPO | 82.52 | Not recorded | 69c36c3b0636e5bf4afc662b |
| Base | 80.33 | Not recorded | 69c36c3b0636e5bf4afc662b |

### PEPOG

Average IoU@50: 83.46. Result ID: 69c3e5e847f34ce924ad79cc.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c3b0636e5bf4afc662b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c36c3b0636e5bf4afc662b.md>)

[Implementation](<https://github.com/xzxxntxdy/PEPO>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-3B-Instruct"}. This record does not assert independent reproduction.

### PEPOD

Average IoU@50: 83.1. Result ID: 69c3e5e847f34ce924ad79ce.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c3b0636e5bf4afc662b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c36c3b0636e5bf4afc662b.md>)

[Implementation](<https://github.com/xzxxntxdy/PEPO>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-3B-Instruct"}. This record does not assert independent reproduction.

### GRPO

Average IoU@50: 82.6. Result ID: 69c3e5e847f34ce924ad79cb.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c3b0636e5bf4afc662b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a761e209131cea8363f.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-3B-Instruct"}. This record does not assert independent reproduction.

### DAPO

Average IoU@50: 82.52. Result ID: 69c3e5e847f34ce924ad79cd.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c3b0636e5bf4afc662b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78a81e209131cea79ac6.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-3B-Instruct"}. This record does not assert independent reproduction.

### Base

Average IoU@50: 80.33. Result ID: 69c3e5e847f34ce924ad79ca.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c3b0636e5bf4afc662b.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-3B-Instruct","Protocol":"zero-shot"}. This record does not assert independent reproduction.

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