HyperAIHyperAI超神经

Command Palette

Search for a command to run...

算力平台

Visual Question Answering On Vqa V2 Val

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 Title
BLIP-2 ViT-G FlanT5 XXL (zero-shot)65.2BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
PNP-VQA63.3Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
BLIP-2 ViT-G FlanT5 XL (zero-shot)63.1BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
BLIP-2 ViT-L FlanT5 XL (zero-shot)62.6BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
BLIP-2 ViT-G OPT 6.7B (zero-shot)54.3BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
BLIP-2 ViT-G OPT 2.7B (zero-shot)53.5BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
BLIP-2 ViT-L OPT 2.7B (zero-shot)50.1BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
Few VLM (zero-shot)47.7A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models
MetaLM41.1Language Models are General-Purpose Interfaces
VLKD(ViT-B/16)38.6Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation
Frozen29.5Multimodal Few-Shot Learning with Frozen Language Models
0 of 11 row(s) selected.