# Visual Question Answering on ImageNet

Source: [Visual Question Answering on ImageNet](<https://www.sota2.com/research/sota/visual-question-answering-on-imagenet>)

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

Data updated: 2026-03-30T07:32:50.909Z

Evaluation of Visual Question Answering performance using the standard ImageNet dataset.

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) | ImageNet |
| Metric | Normalized Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

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

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

## Recorded results

| Method | Normalized Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| TARA-Variant A | 60.5 | Not recorded | 69ca036c0636e5bf4afc9280 |
| TARA-Variant B | 59.6 | Not recorded | 69ca036c0636e5bf4afc9280 |
| TIES | 54.8 | Not recorded | 69ca036c0636e5bf4afc9280 |
| AdaMerging | 47 | Not recorded | 69ca036c0636e5bf4afc9280 |
| KnOTS-TIES | 44.8 | Not recorded | 69ca036c0636e5bf4afc9280 |
| TA | 43.6 | Not recorded | 69ca036c0636e5bf4afc9280 |

### TARA-Variant A

Normalized Accuracy: 60.5. Result ID: 69ca271147f34ce924b274f2.

[Reporting paper](<https://www.sota2.com/research/paper/69ca036c0636e5bf4afc9280.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ca036c0636e5bf4afc9280.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA","Adapter Rank":"16","Optimization Strategy":"gradient-based"}. This record does not assert independent reproduction.

### TARA-Variant B

Normalized Accuracy: 59.6. Result ID: 69ca271147f34ce924b274f3.

[Reporting paper](<https://www.sota2.com/research/paper/69ca036c0636e5bf4afc9280.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ca036c0636e5bf4afc9280.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA","Adapter Rank":"16","Optimization Strategy":"gradient-based"}. This record does not assert independent reproduction.

### TIES

Normalized Accuracy: 54.8. Result ID: 69ca271147f34ce924b274ef.

[Reporting paper](<https://www.sota2.com/research/paper/69ca036c0636e5bf4afc9280.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4ecd8.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA","Adapter Rank":"16","Optimization Strategy":"gradient-free"}. This record does not assert independent reproduction.

### AdaMerging

Normalized Accuracy: 47. Result ID: 69ca271147f34ce924b274f1.

[Reporting paper](<https://www.sota2.com/research/paper/69ca036c0636e5bf4afc9280.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73691e209131cea5c535.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA","Adapter Rank":"16","Optimization Strategy":"gradient-based"}. This record does not assert independent reproduction.

### KnOTS-TIES

Normalized Accuracy: 44.8. Result ID: 69ca271147f34ce924b274f0.

[Reporting paper](<https://www.sota2.com/research/paper/69ca036c0636e5bf4afc9280.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa755b1e209131cea676d6.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA","Adapter Rank":"16","Optimization Strategy":"gradient-free"}. This record does not assert independent reproduction.

### TA

Normalized Accuracy: 43.6. Result ID: 69ca271147f34ce924b274ee.

[Reporting paper](<https://www.sota2.com/research/paper/69ca036c0636e5bf4afc9280.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ef01e209131cea43012.md>)

Recorded evaluation configuration: {"Backbone":"LLaVA","Adapter Rank":"16","Optimization Strategy":"gradient-free"}. This record does not assert independent reproduction.

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