# Remote Sensing Visual Question Answering on RSIVQA (unified)

Source: [Remote Sensing Visual Question Answering on RSIVQA (unified)](<https://www.sota2.com/research/sota/remote-sensing-visual-question-answering-on-rsivqa-unified>)

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

Data updated: 2026-02-26T06:09:04.781Z

Evaluation of model performance on the RSIVQA (unified) dataset for Remote Sensing Visual Question Answering, reporting metrics including Yes/No accuracy, Numerical counts, Other categories, and AA.

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 | Remote Sensing Visual Question Answering |
| Dataset (including any stated split) | RSIVQA (unified) |
| Metric | Yes/No Accuracy |
| 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

- [Yes/No Accuracy](<https://www.sota2.com/research/sota/remote-sensing-visual-question-answering-on-rsivqa-unified.md?metric=Yes%2FNo%20Accuracy>): Higher is better; unit: PERCENT.

- [Numerical Accuracy](<https://www.sota2.com/research/sota/remote-sensing-visual-question-answering-on-rsivqa-unified.md?metric=Numerical%20Accuracy>): Higher is better; unit: PERCENT.

- [Other Category Accuracy](<https://www.sota2.com/research/sota/remote-sensing-visual-question-answering-on-rsivqa-unified.md?metric=Other%20Category%20Accuracy>): Higher is better; unit: PERCENT.

- [AA](<https://www.sota2.com/research/sota/remote-sensing-visual-question-answering-on-rsivqa-unified.md?metric=AA>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Yes/No Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| GRASP | 93.1 | Not recorded | 697846a8a2b28e761d87c588 |
| LoRA | 92 | Not recorded | 697846a8a2b28e761d87c588 |
| DoRA | 91.7 | Not recorded | 697846a8a2b28e761d87c588 |
| VPT | 91.2 | Not recorded | 697846a8a2b28e761d87c588 |
| Adapter | 90.5 | Not recorded | 697846a8a2b28e761d87c588 |
| APrompt | 90.4 | Not recorded | 697846a8a2b28e761d87c588 |
| Prompt Tuning | 89.3 | Not recorded | 697846a8a2b28e761d87c588 |
| Qwen2.5-VL (Base) | 87.3 | Not recorded | 697846a8a2b28e761d87c588 |

### GRASP

Yes/No Accuracy: 93.1. Result ID: 6997953d5698665ec4ead149.

[Reporting paper](<https://www.sota2.com/research/paper/697846a8a2b28e761d87c588.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697846a8a2b28e761d87c588.md>)

Recorded evaluation configuration: {"Trainable Parameters (M)":"4.25","Category":"Prompt-based tuning methods"}. This record does not assert independent reproduction.

### LoRA

Yes/No Accuracy: 92. Result ID: 6997953d5698665ec4ead144.

[Reporting paper](<https://www.sota2.com/research/paper/697846a8a2b28e761d87c588.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b121e209131cea2bf59.md>)

[Implementation](<https://github.com/microsoft/LoRA>)

Recorded evaluation configuration: {"Trainable Parameters (M)":"50.1","Category":"Additive parameter tuning methods"}. This record does not assert independent reproduction.

### DoRA

Yes/No Accuracy: 91.7. Result ID: 6997953d5698665ec4ead145.

[Reporting paper](<https://www.sota2.com/research/paper/697846a8a2b28e761d87c588.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74031e209131cea5f393.md>)

[Implementation](<https://github.com/NVlabs/DoRA>)

Recorded evaluation configuration: {"Trainable Parameters (M)":"50.2","Category":"Additive parameter tuning methods"}. This record does not assert independent reproduction.

### VPT

Yes/No Accuracy: 91.2. Result ID: 6997953d5698665ec4ead148.

[Reporting paper](<https://www.sota2.com/research/paper/697846a8a2b28e761d87c588.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d181e209131cea37ae9.md>)

[Implementation](<https://www.sota2.com/github.com/kmnp/vpt>)

Recorded evaluation configuration: {"Trainable Parameters (M)":"6.70","Category":"Prompt-based tuning methods"}. This record does not assert independent reproduction.

### Adapter

Yes/No Accuracy: 90.5. Result ID: 6997953d5698665ec4ead143.

[Reporting paper](<https://www.sota2.com/research/paper/697846a8a2b28e761d87c588.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65e31e209131cea0d324.md>)

[Implementation](<https://github.com/google-research/adapter-bert>)

Recorded evaluation configuration: {"Trainable Parameters (M)":"16.7","Category":"Additive parameter tuning methods"}. This record does not assert independent reproduction.

### APrompt

Yes/No Accuracy: 90.4. Result ID: 6997953d5698665ec4ead147.

[Reporting paper](<https://www.sota2.com/research/paper/697846a8a2b28e761d87c588.md>)

Recorded evaluation configuration: {"Trainable Parameters (M)":"16.1","Category":"Prompt-based tuning methods"}. This record does not assert independent reproduction.

### Prompt Tuning

Yes/No Accuracy: 89.3. Result ID: 6997953d5698665ec4ead146.

[Reporting paper](<https://www.sota2.com/research/paper/697846a8a2b28e761d87c588.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6aa51e209131cea296c9.md>)

Recorded evaluation configuration: {"Trainable Parameters (M)":"0.41","Category":"Prompt-based tuning methods"}. This record does not assert independent reproduction.

### Qwen2.5-VL (Base)

Yes/No Accuracy: 87.3. Result ID: 6997953d5698665ec4ead142.

[Reporting paper](<https://www.sota2.com/research/paper/697846a8a2b28e761d87c588.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"Trainable Parameters (M)":null}. This record does not assert independent reproduction.

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