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

العربية

Visual Reasoning On Nlvr2 Dev

المقاييس

Accuracy

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	Accuracy	Paper Title	Repository
XFM (base)	87.6	Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding Tasks	-
VLMo	85.64	VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts	-
VisualBERT	66.7	VisualBERT: A Simple and Performant Baseline for Vision and Language	-
VK-OOD	83.9	Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis	-
CoCa	86.1	CoCa: Contrastive Captioners are Image-Text Foundation Models	-
X-VLM (base)	84.41	Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts	-
X2-VLM (large)	88.7	X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks	-
SOHO	76.37	Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning	-
ALBEF (14M)	83.14	Align before Fuse: Vision and Language Representation Learning with Momentum Distillation	-
VK-OOD	84.6	Implicit Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis
ViLT-B/32	75.7	ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision	-
SimVLM	84.53	SimVLM: Simple Visual Language Model Pretraining with Weak Supervision	-
BEiT-3	91.51	Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks	-
X2-VLM (base)	86.2	X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks	-
LXMERT (Pre-train + scratch)	74.9	LXMERT: Learning Cross-Modality Encoder Representations from Transformers	-

0 of 15 row(s) selected.