Scene classification of high-spatial resolution (HSR) images has a wide range of potential applications in various fields, and it has become a research hotspot in remote sensing community. Recently, deep transfer learning-based methods have attracted tremendous attention due to powerful ability of feature extraction. In this paper, a novel architecture termed two-stream feature aggregation deep neural network (TFADNN) is developed for HSR scene classification. The TFADNN method contains two parallel parts, including the stream of discriminative features and the stream of general features. In the first stream, the fully connected layers of pre-trained CNNs are replaced by a global average pooling layer to remove the limitation on the size of input images. As for the second stream, the multi-scale nonlinear encoding based bag-of-visual-words (MNBoVW) model is proposed to process convolutional features, and the global representations can be obtained. Then, weighted fusion is adopted to integrate two-stream features. As a result, the TFADNN method can learn the discriminative features from HSR images with arbitrary sizes, and the experimental results on two challenging datasets indicate that the TFADNN method achieves satisfactory classification performance compared with some state-of-the-art methods.

高空间分辨率（HSR）图像的场景分类在各个领域都有广泛的潜在应用，已成为遥感界的研究热点。近来，基于深度转移学习的方法由于强大的特征提取能力而备受关注。在本文中，开发了一种称为两流特征聚合深度神经网络（TFADNN）的新颖体系结构用于HSR场景分类。TFADNN方法包含两个平行部分，包括判别特征流和一般特征流。在第一流中，预先训练的CNN的完全连接层被全局平均池化层替换，以消除对输入图像大小的限制。至于第二流 提出了一种基于多尺度非线性编码的视觉词袋（MNBoVW）模型来处理卷积特征，并可以得到全局表示。然后，采用加权融合来融合两流特征。结果，TFADNN方法可以从任意大小的HSR图像中学习判别特征，并且在两个具有挑战性的数据集上的实验结果表明，TFADNN方法与某些最新方法相比具有令人满意的分类性能。