# Visual Question Answering on AdVQA Near OOD

Source: [Visual Question Answering on AdVQA Near OOD](<https://www.sota2.com/research/sota/visual-question-answering-on-advqa-near-ood>)

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

Data updated: 2026-02-26T05:30:06.955Z

Evaluation of model performance on the AdVQA Near OOD dataset for Visual Question Answering, measured using 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 | Visual Question Answering |
| Dataset (including any stated split) | AdVQA Near OOD |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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/visual-question-answering-on-advqa-near-ood.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Adam-SPD(LORA) | 50.9 | Not recorded | 68fa75841e209131cea6855b |
| Vanilla FT(LORA) | 49.82 | Not recorded | 68fa75841e209131cea6855b |
| LP-FT(LORA) | 45.68 | Not recorded | 68fa75841e209131cea6855b |
| WiSE-FT(LORA) | 43.95 | Not recorded | 68fa75841e209131cea6855b |
| Linear Prob. | 42.9 | Not recorded | 68fa75841e209131cea6855b |
| Zero-Shot | 30.46 | Not recorded | 68fa75841e209131cea6855b |

### Adam-SPD(LORA)

Accuracy: 50.9. Result ID: 6993cd143a6c31484918a1f7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75841e209131cea6855b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75841e209131cea6855b.md>)

[Implementation](<https://github.com/GT-RIPL/Selective-Projection-Decay.git>)

Recorded evaluation configuration: {"Backbone":"PaliGemma-3B"}. This record does not assert independent reproduction.

### Vanilla FT(LORA)

Accuracy: 49.82. Result ID: 6993cd143a6c31484918a1f3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75841e209131cea6855b.md>)

Recorded evaluation configuration: {"Backbone":"PaliGemma-3B"}. This record does not assert independent reproduction.

### LP-FT(LORA)

Accuracy: 45.68. Result ID: 6993cd143a6c31484918a1f5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75841e209131cea6855b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bdf1e209131cea30c50.md>)

Recorded evaluation configuration: {"Backbone":"PaliGemma-3B"}. This record does not assert independent reproduction.

### WiSE-FT(LORA)

Accuracy: 43.95. Result ID: 6993cd143a6c31484918a1f6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75841e209131cea6855b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cd31e209131cea3601a.md>)

[Implementation](<https://github.com/mlfoundations/wise-ft>)

Recorded evaluation configuration: {"Backbone":"PaliGemma-3B"}. This record does not assert independent reproduction.

### Linear Prob.

Accuracy: 42.9. Result ID: 6993cd143a6c31484918a1f4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75841e209131cea6855b.md>)

Recorded evaluation configuration: {"Backbone":"PaliGemma-3B"}. This record does not assert independent reproduction.

### Zero-Shot

Accuracy: 30.46. Result ID: 6993cd143a6c31484918a1f2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75841e209131cea6855b.md>)

Recorded evaluation configuration: {"Backbone":"PaliGemma-3B"}. This record does not assert independent reproduction.

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