更大并不总是更好？资源受限下小物体检测的效率分析
When Bigger is Worse: A Practitioner's Guide to Model Selection Under Data Scarcity
AI总结：
在资源受限的地球观测中，YOLO11N在效率和准确率上均优于其他模型，揭示了更大模型未必更优的结论。
摘要：
缩放定律假设在更多数据上训练更大的模型总能优于更小的模型——这一假设推动了计算机视觉中的模型选择，但在资源受限的地球观测（EO）中尚未得到验证。我们系统地分析了三个缩放维度：模型大小、数据集大小和输入分辨率，在马达加加的屋顶光伏检测任务中。通过优化模型效率（mAP$_{50}$每单位模型大小），我们发现了一种一致的效率反转：YOLO11N在效率（比YOLO11X高24倍）和绝对mAP$_{50}$（0.617）方面均最高。分辨率是主要的资源分配杠杆（+120%效率提升），而额外数据在低分辨率下收益微乎其微。这些发现对部署目标具有鲁棒性：小型高分辨率配置在所有44种设置的联合准确率-吞吐量空间中均占优，不存在需要权衡的tradeoff。在数据稀缺的EO中，更大并不只是不必要的：它可能更差。
英文摘要：
Scaling laws assume larger models trained on more data consistently outperform smaller ones -- an assumption that drives model selection in computer vision but remains untested in resource-constrained Earth observation (EO). We conduct a systematic efficiency analysis across three scaling dimensions: model size, dataset size, and input resolution, on rooftop photovoltaic (PV) detection in Madagascar, yielding 180 training runs across 60 configurations. Optimizing for model efficiency (mAP$_{50}$ per unit of model size), we find a consistent efficiency inversion: YOLO11N achieves the highest efficiency ($22\times$ higher than YOLO11X) with no accuracy penalty: it reaches the second highest absolute mAP$_{50}$ (0.459), outperforming all models except YOLO11S by a margin smaller than run-to-run variance, directly contradicting the scaling prior. Resolution is the dominant resource allocation lever: moving from 416 px to 1280 px at 10 % of the data matches the efficiency gain of collecting the full dataset at low resolution. These findings are robust to the deployment objective: small high-resolution configurations are Pareto-dominant across all 60 experimental setups in the joint accuracy-throughput space, leaving no tradeoff to resolve. In data-scarce EO, the scaling prior does not just fail: it inverts.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
