Visual Question Answering On Vizwiz 2018 1
Metriken
overall
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | overall |
|---|---|
| towards-vqa-models-that-can-read | 54.72 |
| lxmert-learning-cross-modality-encoder | 55.4 |
| decoupled-box-proposal-and-featurization-with | 53.68 |
| Modell 4 | 45.53 |
| Modell 5 | 51.61 |
| Modell 6 | 47.6 |
| Modell 7 | 51.71 |
| Modell 8 | 47.32 |
| Modell 9 | 54.93 |
| Modell 10 | 52.23 |