List your company

Visual Question Answering on GQA 22

65.3AccuracyMipha-3B+ (Ours)
37.32444.58751.8559.113Jul 5, 2024

Evaluation results

MethodLinks
Mipha-3B+ (Ours)LM=Phi-2 (2.7B), Res.=384, PT=558K, IT=665K2024.0765.3
Mipha-3BLM=Phi-2 (2.7B), Res.=384, PT=558K, IT=665K2024.0763.9
LLaVA-1.5+ (Ours)LM=Vicuna(7B), Res.=336, PT=558K, IT=665K2024.0763.3
MoE-LLaVA-3.6BLM=Phi-2 (2.7B), Res.=384, PT=558k, IT=1.59M2024.0762.6
Bunny-3BLM=Phi-2 (2.7B), Res.=384, PT=2M, IT=695K2024.0762.5
LLaVA-1.5LM=Vicuna (7B), Res.=336, PT=558K, IT=665K2024.0762
TinyLLaVALM=Phi-2 (2.7B), Res.=384, PT=1.2M, IT=665k2024.0762
LAF-7BLM=Vicuna (7B), Res.=336, PT=558K, IT=665K2024.0760.5
Qwen-VLLM=Qwen (7B), Res.=448, PT=1.4B, IT=50M2024.0759.3
Imp-v1LM=Phi-2 (2.7B), Res.=384, PT=558K, IT=665K2024.0758.6
Qwen-VL-ChatLM=Qwen (7B), Res.=448, PT=1.4B, IT=50M2024.0757.5
mPLUG-Owl2LM=LLAMA (7B), Res.=448, PT=400M, IT=1.23M2024.0756.1
InstructBLIPLM=Vicuna (13B), Res.=224, PT=129M, IT=1.2M2024.0749.5
InstructBLIPLM=Vicuna (7B), Res.=224, PT=129M, IT=1.2M2024.0749.2
IDEFICS-80BLM=LLaMA (65B), Res.=224, PT=353M, IT=1M2024.0745.2
BLIP-2LM=Vicuna (13B), Res.=224, PT=129M, IT=-2024.0741
IDEFICS-9BLM=LLaMA (7B), Res.=224, PT=353M, IT=1M2024.0738.4