# Remote Sensing Visual Question Answering on RSVQA-LR unified

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

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

Data updated: 2026-02-26T05:39:58.381Z

Evaluation of model performance on the RSVQA-LR unified dataset for Remote Sensing Visual Question Answering, reporting metrics including Count, R/U, Presence, Comparison, 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) | RSVQA-LR unified |
| Metric | Count |
| Unit | SCALAR |
| 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

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

- [R/U Score](<https://www.sota2.com/research/sota/remote-sensing-visual-question-answering-on-rsvqa-lr-unified.md?metric=R%2FU%20Score>): Higher is better; unit: PERCENT.

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

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

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

## Recorded results

| Method | Count | Result date | Report paper |
| --- | --- | --- | --- |
| GRASP | 31.1 | Not recorded | 697846a8a2b28e761d87c588 |
| VPT | 30.3 | Not recorded | 697846a8a2b28e761d87c588 |
| DoRA | 30 | Not recorded | 697846a8a2b28e761d87c588 |
| LoRA | 29.5 | Not recorded | 697846a8a2b28e761d87c588 |
| Adapter | 27.6 | Not recorded | 697846a8a2b28e761d87c588 |
| APrompt | 23.4 | Not recorded | 697846a8a2b28e761d87c588 |
| Prompt Tuning | 22.3 | Not recorded | 697846a8a2b28e761d87c588 |
| Qwen2.5-VL (Base) | 20.9 | Not recorded | 697846a8a2b28e761d87c588 |

### GRASP

Count: 31.1. Result ID: 6997953d5698665ec4ead139.

[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.

### VPT

Count: 30.3. Result ID: 6997953d5698665ec4ead138.

[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.

### DoRA

Count: 30. Result ID: 6997953d5698665ec4ead135.

[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.

### LoRA

Count: 29.5. Result ID: 6997953d5698665ec4ead134.

[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.

### Adapter

Count: 27.6. Result ID: 6997953d5698665ec4ead133.

[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

Count: 23.4. Result ID: 6997953d5698665ec4ead137.

[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

Count: 22.3. Result ID: 6997953d5698665ec4ead136.

[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)

Count: 20.9. Result ID: 6997953d5698665ec4ead132.

[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.