对比了标注训练与零样本模型在目标检测中的成本效益，发现高推理量下标注模型更划算。
When Does Supervised Training Pay Off? The Hidden Economics of Object Detection in the Era of Vision-Language Models
- 比较YOLO标注模型与Gemini/GPT-4零样本模型的总拥有成本
- 标注模型在超5500万次推理后才回本，且仅在稳定类别下有优势
- 低推理量或类别多变时，零样本模型单位检测成本更低
目标检测传统上依赖昂贵的人工标注。本文首次全面分析监督式YOLO与零样本视觉语言模型（Gemini Flash 2.5和GPT-4）的成本效益。在5,000张分层COCO图像和500张多样产品图像上评估，并结合总拥有成本建模，推导出架构选择的盈亏平衡点。结果表明，在标准类别上，监督式YOLO准确率达91.2%，而Gemini为68.5%，GPT-4为71.3%；100类系统的标注成本为$10,800，准确率优势仅在超过5500万次推理后（即日均151,000次，持续一年）才体现。在多样化产品类别上，Gemini准确率为52.3%，GPT-4为55.1%，而监督式YOLO无法识别未训练类别。在10万次推理时，单位正确检测成本分别为：Gemini $0.00050，GPT-4 $0.00067，YOLO $0.143。我们提供决策框架，指出最优架构选择取决于推理量、类别稳定性、预算和精度要求。
原文摘要 · Abstract (English)
Object detection traditionally relies on costly manual annotation. We present the first comprehensive cost-effectiveness analysis comparing supervised YOLO and zero-shot vision-language models (Gemini Flash 2.5 and GPT-4). Evaluated on 5,000 stratified COCO images and 500 diverse product images, combined with Total Cost of Ownership modeling, we derive break-even thresholds for architecture selection. Results show supervised YOLO attains 91.2% accuracy versus 68.5% for Gemini and 71.3% for GPT-4 on standard categories; the annotation expense for a 100-category system is $10,800, and the accuracy advantage only pays off beyond 55 million inferences (151,000 images/day for one year). On diverse product categories Gemini achieves 52.3% and GPT-4 55.1%, while supervised YOLO cannot detect untrained classes. Cost-per-correct-detection favors Gemini ($0.00050) and GPT-4 ($0.00067) over YOLO ($0.143) at 100,000 inferences. We provide decision frameworks showing that optimal architecture choice depends on inference volume, category stability, budget, and accuracy requirements.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。