Visual Question Answering On Vizwiz 2020 Vqa
Metrics
number
other
overall
unanswerable
yes/no
Results
Performance results of various models on this benchmark
Comparison Table
Model Name | number | other | overall | unanswerable | yes/no |
---|---|---|---|---|---|
Model 1 | 26.83 | 42.29 | 55.93 | 88.95 | 73.45 |
Model 2 | 27.37 | 40.92 | 54.76 | 86.82 | 80.52 |
Model 3 | 18.16 | 28.88 | 44.9 | 84.13 | 60.08 |
video-lavit-unified-video-language-pre | - | - | 56.0 | - | - |
Model 5 | 14.09 | 17.57 | 34.13 | 78.2 | 25.31 |
Model 6 | 17.34 | 27.34 | 44.01 | 85.86 | 53.01 |
pali-a-jointly-scaled-multilingual-language | - | - | 73.3 | - | - |
Model 8 | 18.7 | 26.13 | 41.92 | 81.54 | 49.86 |
Model 9 | 2.71 | 1.21 | 6.25 | 7.13 | 79.85 |
less-is-more-linear-layers-on-clip-features | - | - | 61.64 | - | - |
less-is-more-linear-layers-on-clip-features | - | - | 60.66 | - | - |
Model 12 | 27.1 | 42.3 | 56.33 | 89.49 | 78.89 |
Model 13 | 22.22 | 34.21 | 48.39 | 83.43 | 60.65 |
Model 14 | 20.6 | 34.14 | 49.58 | 88.26 | 59.79 |
Model 15 | 23.04 | 19.05 | 34.96 | 71.45 | 60.08 |
Model 16 | 18.97 | 28.12 | 44.62 | 84.32 | 63.8 |