Visual Question Answering On Vqa V2 Test Std

评估指标

overall

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
BEiT-3	84.03	Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks
mPLUG-Huge	83.62	mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections
ONE-PEACE	82.52	ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
X2-VLM (large)	81.8	X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks
VLMo	81.30	VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts
SimVLM	80.34	SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
X2-VLM (base)	80.2	X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks
VAST	80.19	-	-
VALOR	78.62	VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset
Prompt Tuning	78.53	Prompt Tuning for Generative Multimodal Pretrained Models
Prismer	78.49	Prismer: A Vision-Language Model with Multi-Task Experts
MSR + MS Cog. Svcs., X10 models	77.45	VinVL: Revisiting Visual Representations in Vision-Language Models
MSR + MS Cog. Svcs.	76.63	VinVL: Revisiting Visual Representations in Vision-Language Models
ALBEF (14M)	76.04	Align before Fuse: Vision and Language Representation Learning with Momentum Distillation
BGN, ensemble	75.92	Bilinear Graph Networks for Visual Question Answering	-
ERNIE-ViL-single model	74.93	ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph	-
Single, w/o VLP	74.16	In Defense of Grid Features for Visual Question Answering
Single, w/o VLP	73.86	Deep Multimodal Neural Architecture Search
UNITER (Large)	73.4	UNITER: UNiversal Image-TExt Representation Learning
X-101 grid features + MCAN	72.71	In Defense of Grid Features for Visual Question Answering

0 of 38 row(s) selected.