# Weakly Supervised Referring Expression Comprehension on RefCOCO (testB)

Source: [Weakly Supervised Referring Expression Comprehension on RefCOCO (testB)](<https://www.sota2.com/research/sota/weakly-supervised-referring-expression-comprehension-on-refcoco-testb>)

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

Data updated: 2026-07-07T10:44:16.329Z

Evaluation of Weakly Supervised Referring Expression Comprehension performance on the testB split of the RefCOCO dataset, reporting Accuracy and Inference Speed.

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 | Weakly Supervised Referring Expression Comprehension |
| Dataset (including any stated split) | RefCOCO (testB) |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/weakly-supervised-referring-expression-comprehension-on-refcoco-testb.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Inference Speed (FPS)](<https://www.sota2.com/research/sota/weakly-supervised-referring-expression-comprehension-on-refcoco-testb.md?metric=Inference%20Speed%20(FPS)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SVCR‡ | 70.46 | Not recorded | 6a4c882285dba69fef8b29ad |
| SVCR | 65.55 | Not recorded | 6a4c882285dba69fef8b29ad |
| WeakMCN† | 62.63 | Not recorded | 6a4c882285dba69fef8b29ad |
| WeakMCN\* | 62 | Not recorded | 6a4c882285dba69fef8b29ad |
| DViN | 59.39 | Not recorded | 6a4c882285dba69fef8b29ad |

### SVCR‡

Accuracy: 70.46. Result ID: 6a4cd86d60b88bb339cada19.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882285dba69fef8b29ad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882285dba69fef8b29ad.md>)

Recorded evaluation configuration: {"Backbone":"YOLOv5"}. This record does not assert independent reproduction.

### SVCR

Accuracy: 65.55. Result ID: 6a4cd86d60b88bb339cada18.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882285dba69fef8b29ad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882285dba69fef8b29ad.md>)

Recorded evaluation configuration: {"Backbone":"YOLOv3"}. This record does not assert independent reproduction.

### WeakMCN†

Accuracy: 62.63. Result ID: 6a4cd86d60b88bb339cada16.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882285dba69fef8b29ad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78ea1e209131cea7b34a.md>)

Recorded evaluation configuration: {"Backbone":"YOLOv3","Foundation Model Variant":"ViT-small-SAM"}. This record does not assert independent reproduction.

### WeakMCN\*

Accuracy: 62. Result ID: 6a4cd86d60b88bb339cada15.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882285dba69fef8b29ad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78ea1e209131cea7b34a.md>)

Recorded evaluation configuration: {"Backbone":"YOLOv3","Foundation Model Variant":"ViT-tiny-SAM"}. This record does not assert independent reproduction.

### DViN

Accuracy: 59.39. Result ID: 6a4cd86d60b88bb339cada17.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882285dba69fef8b29ad.md>)

Recorded evaluation configuration: {"Backbone":"YOLOv3"}. This record does not assert independent reproduction.

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