List your company
ResearchFormerly WizWand

Relative Size Prediction on Relative Size zero-shot

85.5AccuracyLaMI
33.70847.15460.674.046Jun 19, 2024
Updated 6mo ago

Evaluation results

MethodLinks
LaMILLM Category=Causal Language Models, Image Augmentation Strategy=Generation2024.0685.5
VaLMLLM Category=Causal Language Models, Image Augmentation Strategy=Retrieval, k=42024.0685
LaMILLM Category=Masked Language Models, Image Augmentation Strategy=Generation2024.0678.4
Z-LaVILLM Category=Causal Language Models, Image Augmentation Strategy=Retrieval2024.0676.8
VokenizationLLM Category=Masked Language Models, Image Augmentation Strategy=Retrieval2024.0672.4
LIVELLM Category=Causal Language Models, Image Augmentation Strategy=Generation2024.0666.7
VaLMLLM Category=Causal Language Models, Image Augmentation Strategy=Retrieval, k=82024.0662.4
GPT-2LLM Category=Causal Language Models, Evaluation Protocol=Zero-shot2024.0643.1
GPT-2 (FT)LLM Category=Causal Language Models, Evaluation Protocol=Fine-tuned2024.0638.2
BERTLLM Category=Masked Language Models, Evaluation Protocol=Zero-shot2024.0638.1
BERT (FT)LLM Category=Masked Language Models, Evaluation Protocol=Fine-tuned2024.0635.7