# Visual Reasoning on NLVR2 loc (val)

Source: [Visual Reasoning on NLVR2 loc (val)](<https://www.sota2.com/research/sota/visual-reasoning-on-nlvr2-loc-val>)

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

Data updated: 2026-02-26T05:27:49.886Z

Evaluation of visual reasoning capabilities on the validation split of the NLVR2 dataset, specifically focusing on the 'loc' subset/configuration, measured by 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 Reasoning |
| Dataset (including any stated split) | NLVR2 loc (val) |
| 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/visual-reasoning-on-nlvr2-loc-val.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| LXMERT+CATT↑ | 77.27 | Not recorded | 68fa696d1e209131cea21f77 |
| LXMERT+CATT | 76.4 | Not recorded | 68fa696d1e209131cea21f77 |
| UNITER | 75.85 | Not recorded | 68fa696d1e209131cea21f77 |
| LXMERT | 74.9 | Not recorded | 68fa696d1e209131cea21f77 |
| LXMERT+ | 74.8 | Not recorded | 68fa696d1e209131cea21f77 |

### LXMERT+CATT↑

Accuracy: 77.27. Result ID: 698da8e98b517eb43322effc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa696d1e209131cea21f77.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa696d1e209131cea21f77.md>)

[Implementation](<https://github.com/yangxuntu/catt>)

Recorded evaluation configuration: {"GPU Hours":"1536 (1080Ti), 1056 (V100)","Pre-training Data (Image / Text)":"0.18M / 9.18M"}. This record does not assert independent reproduction.

### LXMERT+CATT

Accuracy: 76.4. Result ID: 698da8e98b517eb43322effb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa696d1e209131cea21f77.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa696d1e209131cea21f77.md>)

[Implementation](<https://github.com/yangxuntu/catt>)

Recorded evaluation configuration: {"GPU Hours":"960 (1080Ti), 624 (V100)","Pre-training Data (Image / Text)":"0.18M / 9.18M"}. This record does not assert independent reproduction.

### UNITER

Accuracy: 75.85. Result ID: 698da8e98b517eb43322effa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa696d1e209131cea21f77.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67f91e209131cea1989f.md>)

[Implementation](<https://github.com/ChenRocks/UNITER>)

Recorded evaluation configuration: {"GPU Hours":"882 (V100)","Pre-training Data (Image / Text)":"4.20M / 9.58M"}. This record does not assert independent reproduction.

### LXMERT

Accuracy: 74.9. Result ID: 698da8e98b517eb43322eff8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa696d1e209131cea21f77.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66cc1e209131cea12644.md>)

[Implementation](<https://github.com/airsplay/lxmert>)

Recorded evaluation configuration: {"GPU Hours":"960 (titan xp)","Pre-training Data (Image / Text)":"0.18M / 9.18M"}. This record does not assert independent reproduction.

### LXMERT+

Accuracy: 74.8. Result ID: 698da8e98b517eb43322eff9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa696d1e209131cea21f77.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66cc1e209131cea12644.md>)

[Implementation](<https://github.com/airsplay/lxmert>)

Recorded evaluation configuration: {"GPU Hours":"816 (1080Ti)","Pre-training Data (Image / Text)":"0.18M / 9.18M"}. This record does not assert independent reproduction.

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