الرئيسية الأخبار أحدث الأوراق البحثية الدروس مجموعات البيانات الموسوعة SOTA نماذج LLM لوحة الأداء GPU الفعاليات

العربية

Visual Question Answering On Vqa V2 Test Dev 1

المقاييس

Accuracy

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	Accuracy	Paper Title	Repository
Florence	80.16	Florence: A New Foundation Model for Computer Vision
LXMERT (low-magnitude pruning)	70.72	LXMERT Model Compression for Visual Question Answering
VK-OOD	76.8	Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis
BLIP-2 ViT-G OPT 6.7B (fine-tuned)	82.30	BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
BLIP-2 ViT-G OPT 2.7B (fine-tuned)	81.74	BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
LocVLM-L	56.2	Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs
BLIP-2 ViT-G FlanT5 XL (fine-tuned)	81.66	BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
OFA	82.0	OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
Aurora (ours, r=64)	77.69	-	-
CoCa	82.3	CoCa: Contrastive Captioners are Image-Text Foundation Models
mPLUG-2	81.11	mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video

0 of 11 row(s) selected.