HyperAIHyperAI超神经
首页算力平台文档资讯论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAIHyperAI超神经

Visual Question Answering Vqa On Infoseek

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

Paper TitleRepository
RA-VQAv2 w/ PreFLMR30.65PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers
PaLI-X24PaLI-X: On Scaling up a Multilingual Vision and Language Model
CLIP + FiD20.9Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?
CLIP + PaLM (540B)20.4Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?
PaLI19.7Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?
BLIP214.6BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
InstructBLIP14.5--
0 of 7 row(s) selected.
Visual Question Answering Vqa On Infoseek | SOTA | HyperAI超神经