Visual Question Answering On Vqa V2 Val

Métriques

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

		Paper Title
BLIP-2 ViT-G FlanT5 XXL (zero-shot)	65.2	BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
PNP-VQA	63.3	Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
BLIP-2 ViT-G FlanT5 XL (zero-shot)	63.1	BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
BLIP-2 ViT-L FlanT5 XL (zero-shot)	62.6	BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
BLIP-2 ViT-G OPT 6.7B (zero-shot)	54.3	BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
BLIP-2 ViT-G OPT 2.7B (zero-shot)	53.5	BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
BLIP-2 ViT-L OPT 2.7B (zero-shot)	50.1	BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
Few VLM (zero-shot)	47.7	A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models
MetaLM	41.1	Language Models are General-Purpose Interfaces
VLKD(ViT-B/16)	38.6	Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation
Frozen	29.5	Multimodal Few-Shot Learning with Frozen Language Models

0 of 11 row(s) selected.

Visual Question Answering On Vqa V2 Val | SOTA | HyperAI