# Referring Object Detection on RefCOCOg (val)

Source: [Referring Object Detection on RefCOCOg (val)](<https://www.sota2.com/research/sota/referring-object-detection-on-refcocog-val>)

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

Data updated: 2026-03-26T14:35:06.955Z

Evaluation of Referring Object Detection performance on the validation split of the RefCOCOg dataset, typically measured using accuracy metrics like Top-1 accuracy.

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 Object Detection |
| Dataset (including any stated split) | RefCOCOg (val) |
| Metric | Top-1 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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

- [Top-1 Accuracy](<https://www.sota2.com/research/sota/referring-object-detection-on-refcocog-val.md?metric=Top-1%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| HeROD-G | 85.4 | Not recorded | 69c4bdb80636e5bf4afc778a |
| Grounding DINO\* | 84.66 | Not recorded | 69c4bdb80636e5bf4afc778a |
| DQ-DETR | 82.76 | Not recorded | 69c4bdb80636e5bf4afc778a |
| MDETR | 81.64 | Not recorded | 69c4bdb80636e5bf4afc778a |
| RefTR | 79.25 | Not recorded | 69c4bdb80636e5bf4afc778a |
| VILLA-L | 76.18 | Not recorded | 69c4bdb80636e5bf4afc778a |
| HeROD-U | 69.06 | Not recorded | 69c4bdb80636e5bf4afc778a |
| TransVG | 68.67 | Not recorded | 69c4bdb80636e5bf4afc778a |
| MAttNet | 66.58 | Not recorded | 69c4bdb80636e5bf4afc778a |
| VGTR | 65.73 | Not recorded | 69c4bdb80636e5bf4afc778a |
| UNINEXT\* | 64.18 | Not recorded | 69c4bdb80636e5bf4afc778a |
| Grounding DINO\* | 60.38 | Not recorded | 69c4bdb80636e5bf4afc778a |

### HeROD-G

Top-1 Accuracy: 85.4. Result ID: 69c543fd47f34ce924af31ef.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdb80636e5bf4afc778a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c4bdb80636e5bf4afc778a.md>)

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

### Grounding DINO\*

Top-1 Accuracy: 84.66. Result ID: 69c543fd47f34ce924af31ee.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdb80636e5bf4afc778a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74311e209131cea6055d.md>)

[Implementation](<https://github.com/IDEA-Research/GroundingDINO>)

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

### DQ-DETR

Top-1 Accuracy: 82.76. Result ID: 69c543fd47f34ce924af31ea.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdb80636e5bf4afc778a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e1f1e209131cea3df1e.md>)

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

### MDETR

Top-1 Accuracy: 81.64. Result ID: 69c543fd47f34ce924af31e9.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdb80636e5bf4afc778a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af51e209131cea2b5a9.md>)

[Implementation](<https://github.com/ashkamath/mdetr>)

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

### RefTR

Top-1 Accuracy: 79.25. Result ID: 69c543fd47f34ce924af31e8.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdb80636e5bf4afc778a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a611e209131cea27dec.md>)

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

### VILLA-L

Top-1 Accuracy: 76.18. Result ID: 69c543fd47f34ce924af31e7.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdb80636e5bf4afc778a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a01e209131cea1d368.md>)

[Implementation](<https://github.com/zhegan27/VILLA>)

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

### HeROD-U

Top-1 Accuracy: 69.06. Result ID: 69c543fd47f34ce924af31ec.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdb80636e5bf4afc778a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c4bdb80636e5bf4afc778a.md>)

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

### TransVG

Top-1 Accuracy: 68.67. Result ID: 69c543fd47f34ce924af31e6.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdb80636e5bf4afc778a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b941e209131cea2f03e.md>)

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

### MAttNet

Top-1 Accuracy: 66.58. Result ID: 69c543fd47f34ce924af31e4.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdb80636e5bf4afc778a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa642c1e209131cea031d4.md>)

[Implementation](<https://github.com/lichengunc/MAttNet>)

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

### VGTR

Top-1 Accuracy: 65.73. Result ID: 69c543fd47f34ce924af31e5.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdb80636e5bf4afc778a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bfe1e209131cea3181e.md>)

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

### UNINEXT\*

Top-1 Accuracy: 64.18. Result ID: 69c543fd47f34ce924af31eb.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdb80636e5bf4afc778a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70541e209131cea4a478.md>)

[Implementation](<https://github.com/MasterBin-IIAU/UNINEXT>)

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

### Grounding DINO\*

Top-1 Accuracy: 60.38. Result ID: 69c543fd47f34ce924af31ed.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bdb80636e5bf4afc778a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74311e209131cea6055d.md>)

[Implementation](<https://github.com/IDEA-Research/GroundingDINO>)

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

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