Remote Sensing Image Classification via Improved Cross-Entropy Loss and Transfer Learning Strategy Based on Deep Convolutional Neural Networks
Remote Sensing Image Classification via Improved Cross-Entropy Loss and Transfer Learning Strategy Based on Deep Convolutional Neural Networks
复制标题
DOI：
10.1109/lgrs.2019.2937872
复制
发表时间：
2020-06-01
影响因子：
4.8
通讯作者：
Mohammadi, Karim
中科院分区：
文献类型：
--
作者：
Bahri, Ali;Majelan, Sina Ghofrani;Mohammadi, Karim
近年来，深度卷积神经网络（DCNN）在航拍图像分类方面取得了巨大成功，但在该领域，由于其固有的特性，硬图像的存在以及由于使用交叉熵（CE）损失而导致网络对它们的关注较弱，导致航拍图像分类的准确性降低。此外，由于 CNN 中的最后一个卷积层具有高度特定于类别的信息，因此与自适应地对每个通道进行加权相比，对所有通道给予同等重要性会导致提取较少的判别性特征。事实上，数据标记以及在大型数据集上创建真实数据的成本高昂，这是这方面的另一个令人担忧的问题。为了解决这些问题，我们提出了一种新的航空图像分类方法。我们的方法包括提出一个新的损失函数，通过在 CE 中添加一个新项作为惩罚项来增强网络对困难示例的关注，从而带来最先进的结果；设计一个新的多层感知器（MLP）作为分类器，其中使用的注意力机制通过自适应地对每个通道加权来提取更多的判别性特征；在航拍图像领域首次采用神经架构搜索网络移动（NASNet Mobile）作为特征描述符来应用迁移学习策略，可以减轻上述成本。如结果所示，我们提出的方法优于现有的基线方法，并在所有三个数据集上实现了最先进的结果。
Recently, deep convolutional neural networks (DCNNs) have gained great success in classifying aerial images, but in this area, the existence of the hard images, due to their innate characteristics, and weak focus of the network on them, due to the use of the cross-entropy (CE) loss, lead to reducing the accuracy of classification of aerial images. Moreover, since the last convolutional layer in a CNN has highly class-specific information, giving equal importance to all the channels causes to extract less discriminative features in comparison to weighting each of the channels adaptively. The fact that data labeling as well as creating ground truth on large data set is expensive is another point of concern in this regard. To address these problems, we have proposed a novel method for classification of aerial images. Our method includes proposing a new loss function, which enhances the focus of the network on hard examples by adding a new term to CE as a penalty term, bringing about the state-of-the-art results; designing a new multilayer perceptron (MLP) as a classifier, in which the used attention mechanism extracts more discriminative features by weighting each of the channels adaptively; and applying transfer learning strategy by adopting neural architecture search network mobile (NASNet Mobile) as a feature descriptor for the first time in the field of aerial images, which can mitigate the aforementioned costs. As indicated in the results, our proposed method outperforms the existing baseline methods and achieves state-of-the-art results on all three data sets.