Image Captioning On Nocaps Xd In Domain
Metriken
B1
B2
B3
B4
CIDEr
METEOR
ROUGE-L
SPICE
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
Modellname | B1 | B2 | B3 | B4 | CIDEr | METEOR | ROUGE-L | SPICE |
---|---|---|---|---|---|---|---|---|
Modell 1 | 79.14 | 62.18 | 43.04 | 25.67 | 82.86 | 26.82 | 55.37 | 11.9 |
git-a-generative-image-to-text-transformer | 88.86 | 75.86 | 59.94 | 41.1 | 124.18 | 33.83 | 63.82 | 16.36 |
Modell 3 | 77.65 | 59.58 | 39.86 | 22.83 | 76.02 | 26.35 | 53.98 | 11.8 |
Modell 4 | 77.68 | 60.34 | 41.5 | 24.57 | 74.27 | 26.04 | 54.42 | 11.47 |
vivo-surpassing-human-performance-in-novel | 82.94 | 67.56 | 49.66 | 32.07 | 100.62 | 30.62 | 59.43 | 14.7 |
Modell 6 | 81.84 | 64.09 | 44.03 | 25.66 | 90.73 | 28.39 | 55.41 | 13.5 |
Modell 7 | 76.49 | 56.2 | 33.73 | 15.14 | 62.96 | 23.68 | 50.84 | 10.12 |
Modell 8 | 75.91 | 56.78 | 35.58 | 17.39 | 60.89 | 23.8 | 51.42 | 9.81 |
git-a-generative-image-to-text-transformer | 88.55 | 76.1 | 60.53 | 41.65 | 122.4 | 33.41 | 64.02 | 16.18 |
Modell 10 | 76.89 | 57.3 | 37.78 | 21.49 | 80.61 | 28.53 | 53.47 | 14.99 |
Modell 11 | 85.33 | 70.44 | 52.99 | 34.02 | 106.36 | 31.18 | 60.67 | 15.51 |