Visual Reasoning On Nlvr2 Test

Métriques

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

		Paper Title
BEiT-3	92.58	Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks
X2-VLM (large)	89.4	X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks
XFM (base)	88.4	Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding Tasks
CoCa	87.0	CoCa: Contrastive Captioners are Image-Text Foundation Models
X2-VLM (base)	87.0	X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks
VLMo	86.86	VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts
SimVLM	85.15	SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
X-VLM (base)	84.76	Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts
BLIP-129M	83.09	BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
ALBEF (14M)	82.55	Align before Fuse: Vision and Language Representation Learning with Momentum Distillation
UNITER (Large)	79.5	UNITER: UNiversal Image-TExt Representation Learning
SOHO	77.32	Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning
LXMERT	76.2	LXMERT: Learning Cross-Modality Encoder Representations from Transformers
ViLT-B/32	76.13	ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision

0 of 14 row(s) selected.

Visual Reasoning On Nlvr2 Test | SOTA | HyperAI