Deep Learning Earth Observation Classification Using ImageNet Pretrained Networks
Deep Learning Earth Observation Classification Using ImageNet Pretrained Networks
复制标题
DOI：
10.1109/lgrs.2015.2499239
复制
发表时间：
2016-01-01
影响因子：
4.8
通讯作者：
Stilla, Uwe
中科院分区：
文献类型：
--
作者：
Marmanis, Dimitrios;Datcu, Mihai;Stilla, Uwe
当提供足够大的数据集和相应标签时，卷积神经网络 (CNN) 等深度学习方法可以提供高度准确的分类结果。然而，将 CNN 与有限的标记数据一起使用可能会出现问题，因为这会导致广泛的过度拟合。在这封信中，我们提出了一种新颖的方法，考虑了为解决完全不同的分类问题（即 ImageNet 挑战）而设计的预训练 CNN，并利用它来提取初始表示集。然后，将派生的表示及其类别标签转移到有监督的 CNN 分类器中，从而有效地训练系统。通过这个两阶段框架，我们成功地解决了端到端处理方案中的有限数据问题。与加州大学默塞德分校土地利用基准的比较结果证明，我们的方法明显优于之前的最佳结果，将整体准确率从 83.1% 提高到 92.4%。除了统计改进之外，我们的方法还引入了一种新颖的特征融合算法，该算法通过使用简单且计算高效的方法有效地处理大数据维度。
Deep learning methods such as convolutional neural networks (CNNs) can deliver highly accurate classification results when provided with large enough data sets and respective labels. However, using CNNs along with limited labeled data can be problematic, as this leads to extensive overfitting. In this letter, we propose a novel method by considering a pretrained CNN designed for tackling an entirely different classification problem, namely, the ImageNet challenge, and exploit it to extract an initial set of representations. The derived representations are then transferred into a supervised CNN classifier, along with their class labels, effectively training the system. Through this two-stage framework, we successfully deal with the limited-data problem in an end-to-end processing scheme. Comparative results over the UC Merced Land Use benchmark prove that our method significantly outperforms the previously best stated results, improving the overall accuracy from 83.1% up to 92.4%. Apart from statistical improvements, our method introduces a novel feature fusion algorithm that effectively tackles the large data dimensionality by using a simple and computationally efficient approach.