Visual Question Answering on VQA-HAT ID
38.75AccuracyVISFIS
Evaluation results
| Method | Links | |
|---|---|---|
| VISFISModel Architecture=UpDn2022.06 | 38.75 | |
| Singla et al.Model Architecture=UpDn2022.06 | 38.28 | |
| Suff-RandomModel Architecture=UpDn2022.06 | 37.99 | |
| Simpson et al.Model Architecture=UpDn2022.06 | 37.66 | |
| BaselineModel Architecture=UpDn2022.06 | 37.53 | |
| Wu and MooneyModel Architecture=UpDn2022.06 | 37.24 | |
| w/ Rand. Supervis.Model Architecture=UpDn2022.06 | 37.16 | |
| Selvaraju et al.Model Architecture=UpDn2022.06 | 36.93 | |
| Chang et al.Model Architecture=UpDn2022.06 | 32.55 |