firethehole

Reported on 32 benchmarks across 1 task

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing32 results

Image Captioningonnocaps near-domain
B1
81.62
best: 88.9 (GIT2, Single Model)
Image Captioningonnocaps near-domain
B2
66.65
best: 75.86 (GIT2, Single Model)
Image Captioningonnocaps near-domain
B3
49.39
best: 58.99 (PaLI)
Image Captioningonnocaps near-domain
B4
31.42
best: 39.98 (PaLI)
Image Captioningonnocaps near-domain
CIDEr
99.51
best: 125.51 (GIT2, Single Model)
Image Captioningonnocaps near-domain
METEOR
30.48
best: 33.47 (PaLI)
Image Captioningonnocaps near-domain
ROUGE-L
58.83
best: 63.99 (PaLI)
Image Captioningonnocaps near-domain
SPICE
14.88
best: 16.11 (GIT2, Single Model)
Image Captioningonnocaps entire
B1
80.77
best: 88.1 (GIT, Single Model)
Image Captioningonnocaps entire
B2
65.55
best: 74.81 (GIT, Single Model)
Image Captioningonnocaps entire
B3
48.14
best: 57.68 (GIT, Single Model)
Image Captioningonnocaps entire
B4
30.2
best: 37.71 (CoCa - Google Brain)
Image Captioningonnocaps entire
CIDEr
97.61
best: 126.8 (Lyrics)
Image Captioningonnocaps entire
METEOR
30.07
best: 32.5 (GIT, Single Model)
Image Captioningonnocaps entire
ROUGE-L
58.25
best: 63.12 (GIT, Single Model)
Image Captioningonnocaps entire
SPICE
14.74
best: 15.94 (GIT, Single Model)
Image Captioningonnocaps out-of-domain
B1
76.65
best: 86.28 (PaLI)
Image Captioningonnocaps out-of-domain
B2
60.06
best: 71.28 (GIT, Single Model)
Image Captioningonnocaps out-of-domain
B3
41.58
best: 52.66 (GIT, Single Model)
Image Captioningonnocaps out-of-domain
B4
22.66
best: 32 (PaLI)
Image Captioningonnocaps out-of-domain
CIDEr
88.54
best: 126.67 (PaLI)
Image Captioningonnocaps out-of-domain
METEOR
27.39
best: 30.99 (PaLI)
Image Captioningonnocaps out-of-domain
ROUGE-L
55.08
best: 61.35 (PaLI)
Image Captioningonnocaps out-of-domain
SPICE
13.87
best: 15.7 (GIT, Single Model)
Image Captioningonnocaps in-domain
B1
81.86
best: 88.86 (GIT2, Single Model)
Image Captioningonnocaps in-domain
B2
67.2
best: 76.1 (GIT, Single Model)
Image Captioningonnocaps in-domain
B3
50.5
best: 60.53 (GIT, Single Model)
Image Captioningonnocaps in-domain
B4
34.11
best: 41.65 (GIT, Single Model)
Image Captioningonnocaps in-domain
CIDEr
99.9
best: 149.1 (PaLI)
Image Captioningonnocaps in-domain
METEOR
31.61
best: 34.22 (PaLI)
Image Captioningonnocaps in-domain
ROUGE-L
59.54
best: 64.39 (PaLI)
Image Captioningonnocaps in-domain
SPICE
15.17
best: 16.36 (GIT2, Single Model)