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

模型名称	overall	Paper Title	Repository
LXMERT	72.5	LXMERT: Learning Cross-Modality Encoder Representations from Transformers	-
2D continuous softmax	66.27	Sparse and Continuous Attention Mechanisms	-
VisualBERT	71	VisualBERT: A Simple and Performant Baseline for Vision and Language	-
X2-VLM (large)	81.8	X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks	-
Image features from bottom-up attention (adaptive K, ensemble)	70.3	Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challenge	-
MCB [11, 12]	62.27	Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering	-
Up-Down	70.34	Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering	-
Prompt Tuning	78.53	Prompt Tuning for Generative Multimodal Pretrained Models	-
MCANed-6	70.9	Deep Modular Co-Attention Networks for Visual Question Answering	-
BEiT-3	84.03	Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks	-
VLMo	81.30	VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts	-
VALOR	78.62	VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset	-
BLOCK	67.9	BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection	-
mPLUG-Huge	83.62	mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections	-
DMN	68.4	Learning to Count Objects in Natural Images for Visual Question Answering	-
BGN, ensemble	75.92	Bilinear Graph Networks for Visual Question Answering	-
SimVLM	80.34	SimVLM: Simple Visual Language Model Pretraining with Weak Supervision	-
VL-BERTLARGE	72.2	VL-BERT: Pre-training of Generic Visual-Linguistic Representations	-
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	-

0 of 38 row(s) selected.