论文标题
多标签遥感图像分类的深度学习损失函数的比较研究
A Comparative Study of Deep Learning Loss Functions for Multi-Label Remote Sensing Image Classification
论文作者
论文摘要
本文分析并比较了多标签遥感（RS）图像场景分类问题的框架中不同的深度学习损失功能。我们考虑七个损失功能：1）跨透明拷贝损失； 2）局灶性损失； 3）加权跨透明拷贝损失； 4）锤损； 5）Huber损失； 6）排名损失； 7）Sparsemax损失。首次以卢比为单位分析所有考虑的损失功能。经过理论分析后，进行了实验分析以比较其考虑的损失函数：1）总体准确性； 2）阶级不平衡意识（与每个类相关的样本的数量有很大变化）； 3）凸性和可不同的性能； 4）学习效率（即收敛速度）。根据我们的分析，得出了一些准则，以适当选择多标签RS场景分类问题中的损失功能。
This paper analyzes and compares different deep learning loss functions in the framework of multi-label remote sensing (RS) image scene classification problems. We consider seven loss functions: 1) cross-entropy loss; 2) focal loss; 3) weighted cross-entropy loss; 4) Hamming loss; 5) Huber loss; 6) ranking loss; and 7) sparseMax loss. All the considered loss functions are analyzed for the first time in RS. After a theoretical analysis, an experimental analysis is carried out to compare the considered loss functions in terms of their: 1) overall accuracy; 2) class imbalance awareness (for which the number of samples associated to each class significantly varies); 3) convexibility and differentiability; and 4) learning efficiency (i.e., convergence speed). On the basis of our analysis, some guidelines are derived for a proper selection of a loss function in multi-label RS scene classification problems.
