Visual Question Answering On Vqa V2 Test Std

评估指标

overall

评测结果

各个模型在此基准测试上的表现结果

比较表格

模型名称	overall
lxmert-learning-cross-modality-encoder	72.5
sparse-and-continuous-attention-mechanisms	66.27
visualbert-a-simple-and-performant-baseline	71
x-2-vlm-all-in-one-pre-trained-model-for	81.8
tips-and-tricks-for-visual-question-answering	70.3
making-the-v-in-vqa-matter-elevating-the-role	62.27
bottom-up-and-top-down-attention-for-image	70.34
prompt-tuning-for-generative-multimodal	78.53
deep-modular-co-attention-networks-for-visual-1	70.9
image-as-a-foreign-language-beit-pretraining	84.03
vlmo-unified-vision-language-pre-training	81.30
valor-vision-audio-language-omni-perception	78.62
block-bilinear-superdiagonal-fusion-for	67.9
mplug-effective-and-efficient-vision-language	83.62
learning-to-count-objects-in-natural-images	68.4
graph-reasoning-networks-for-visual-question	75.92
simvlm-simple-visual-language-model	80.34
vl-bert-pre-training-of-generic-visual	72.2
in-defense-of-grid-features-for-visual	74.16
deep-multimodal-neural-architecture-search	73.86
prismer-a-vision-language-model-with-an	78.49
mutan-multimodal-tucker-fusion-for-visual	67.4
vinvl-making-visual-representations-matter-in	76.63
x-2-vlm-all-in-one-pre-trained-model-for	80.2
vinvl-making-visual-representations-matter-in	77.45
in-defense-of-grid-features-for-visual	72.71
uniter-learning-universal-image-text-1	73.4
模型 28	80.19
murel-multimodal-relational-reasoning-for	68.4
bilinear-attention-networks	70.4
ernie-vil-knowledge-enhanced-vision-language	74.93
one-peace-exploring-one-general	82.52
making-the-v-in-vqa-matter-elevating-the-role	25.98
making-the-v-in-vqa-matter-elevating-the-role	44.26
unified-vision-language-pre-training-for	70.7
visual-commonsense-r-cnn	71.49
align-before-fuse-vision-and-language	76.04
190600513	69.7