对比通用与卫星专用模型，发现海量数据比任务特定更有效
Mapping Rio de Janeiro's favelas: general-purpose vs. satellite-specific neural networks
- 用通用预训练模型和卫星专用模型对比检测里约贫民窟
- 通用模型在更大数据集上训练，表现优于专用模型
- 适合关注遥感图像分析与模型泛化能力的研究者
尽管针对非正规住区检测的深度学习方法已存在，但尚未充分挖掘近期预训练神经网络的潜力。本文对比了两种预训练神经网络在检测里约热内卢贫民窟中的表现：1. 在大规模多样化非特定图像数据集上预训练的通用模型；2. 在卫星影像数据上预训练的专用模型。后者虽更契合目标任务，但前者在更大规模的数据集上进行预训练。本研究探讨在城市非正规住区检测任务中，任务特异性与数据量哪个更能带来更优性能。
原文摘要 · Abstract (English)
While deep learning methods for detecting informal settlements have already been developed, they have not yet fully utilized the potential offered by recent pretrained neural networks. We compare two types of pretrained neural networks for detecting the favelas of Rio de Janeiro: 1. Generic networks pretrained on large diverse datasets of unspecific images, 2. A specialized network pretrained on satellite imagery. While the latter is more specific to the target task, the former has been pretrained on significantly more images. Hence, this research investigates whether task specificity or data volume yields superior performance in urban informal settlement detection.
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。