Visual Question Answering On Ok Vqa

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
PaLI-X-VPD	66.8	Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models	-
PaLM-E-562B	66.1	PaLM-E: An Embodied Multimodal Language Model
PaLI-X (Single-task FT)	66.1	PaLI-X: On Scaling up a Multilingual Vision and Language Model
PaLI 17B	64.5	PaLI: A Jointly-Scaled Multilingual Language-Image Model
Prophet	62.5	Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering
RA-VQA-v2 (BLIP 2)	62.08	Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering
A Simple Baseline for KB-VQA	61.2	A Simple Baseline for Knowledge-Based Visual Question Answering	-
PromptCap	60.4	PromptCap: Prompt-Guided Task-Aware Image Captioning
ReVeaL WIT + CC12M + Wikidata + VQA-2	59.1	REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory
Lyrics	58.2	Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects	-
REVIVE (Ensemble)	58.0	REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering
REVIVE (Single)	56.6	REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering
RA-VQA-v2 (T5-large)	54.85	Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering
RA-VQA (T5-large)	54.48	Retrieval Augmented Visual Question Answering with Outside Knowledge
VK-OOD	52.4	Implicit Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis	-
VK-OOD	52.4	Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis
RA-VQA-FrDPR (T5-large)	51.22	Retrieval Augmented Visual Question Answering with Outside Knowledge
Flamingo80B	50.6	Flamingo: a Visual Language Model for Few-Shot Learning
TRiG (T5-Large)	50.50	Transform-Retrieve-Generate: Natural Language-Centric Outside-Knowledge Visual Question Answering	-
HYDRA	48.6	HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning

0 of 37 row(s) selected.