Startseite Neuigkeiten Neueste Forschungsarbeiten Tutorials Datensätze Wiki SOTA LLM-Modelle GPU-Rangliste Veranstaltungen

Deutsch

Visual Question Answering On Gqa Test Dev

Metriken

Accuracy

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	Accuracy	Paper Title	Repository
BLIP-2 ViT-G OPT 2.7B (zero-shot)	34.6	BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
BLIP-2 ViT-G FlanT5 XXL (zero-shot)	44.7	BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
PNP-VQA	41.9	Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
PaLI-X-VPD	67.3	Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models	-
LXMERT (Pre-train + scratch)	60.0	LXMERT: Learning Cross-Modality Encoder Representations from Transformers
BLIP-2 ViT-L FlanT5 XL (zero-shot)	44.4	BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
FewVLM (zero-shot)	29.3	A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models
BLIP-2 ViT-G OPT 6.7B (zero-shot)	36.4	BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
HYDRA	47.9	HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning
NSM	62.95	Learning by Abstraction: The Neural State Machine
Lyrics	62.4	Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects	-
BLIP-2 ViT-L OPT 2.7B (zero-shot)	33.9	BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
single-hop + LCGN (ours)	55.8	Language-Conditioned Graph Networks for Relational Reasoning
CFR	72.1	Coarse-to-Fine Reasoning for Visual Question Answering
BLIP-2 ViT-G FlanT5 XL (zero-shot)	44.2	BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
Video-LaVIT	64.4	Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
CuMo-7B	64.9	CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts

0 of 17 row(s) selected.

Visual Question Answering On Gqa Test Dev | SOTA | HyperAI