List your company

Semantic Object Identification on COST (val)

87.2CS ScoreVCoder LLaVA-1.5-13b
-3.4235220.1037443.63167.15826Dec 21, 2023

Evaluation results

MethodLinks
VCoder LLaVA-1.5-13bInput Tokens=(seg) + (img) + (query)2023.1287.211.6
VCoder LLaVA-1.5-7bInput Tokens=(seg) + (img) + (query)2023.128612.8
COST IT LLaVA-1.5-7bInput Tokens=(img) + (query)2023.1271.928.2
ImCoder LLaVA-1.5-7bInput Tokens=(img) + (img) + (query)2023.1270.827.9
CogVLM-17bInput Tokens=(img) + (query)2023.1240.675.9
LLaVA-1.5-7bInput Tokens=(img) + (query)2023.1238.767.3
GPT-4VInput Tokens=(img) + (query)2023.1238.483
LLaVA-1.5-13bInput Tokens=(img) + (query)2023.1235.868.6
Soft-Prompted LLaVA-1.5-7bInput Tokens=(prompt) + (img) + (query)2023.1226.863
InstructBLIP Vicuna-7bInput Tokens=(img) + (query)2023.1217.591.2
MiniGPT-4 LLaMA-2-7bInput Tokens=(img) + (query)2023.126.294.9
VCoder LLaVA-1.5-13bInput Tokens=(seg) + (img) + (query)2023.120.890.1
VCoder LLaVA-1.5-7bInput Tokens=(seg) + (img) + (query)2023.120.8860.104
ImCoder LLaVA-1.5-7bInput Tokens=(img) + (img) + (query)2023.120.7890.227
COST IT LLaVA-1.5-7bInput Tokens=(img) + (query)2023.120.7870.221
Soft-Prompted LLaVA-1.5-7bInput Tokens=(prompt) + (img) + (query)2023.120.3620.567
CogVLM-17bInput Tokens=(img) + (query)2023.120.3340.675
LLaVA-1.5-7bInput Tokens=(img) + (query)2023.120.3060.601
LLaVA-1.5-13bInput Tokens=(img) + (query)2023.120.250.693
InstructBLIP Vicuna-7bInput Tokens=(img) + (query)2023.120.1420.858
MiniGPT-4 LLaMA-2-7bInput Tokens=(img) + (query)2023.120.0620.922