论文标题
用于分层概念分类的多层密集连接
Multilayer Dense Connections for Hierarchical Concept Classification
论文作者
论文摘要
分类是许多计算机视觉任务（例如对象分类，检测，场景分割）的关键函数。具有单一的密集连接最终层的多项式逻辑回归已成为基于CNN的分类的无处不在技术。尽管这些分类器在输入和一组输出类别类之间投影映射，但它们通常不会对类别进行全面描述。特别是，当基于CNN的图像分类器正确地识别黑猩猩的图像时，其输出并不能阐明黑猩猩是灵长类动物，哺乳动物，Chordate家族和生物的成员。我们提出了一个多层密集的连接性，以通过同一CNN以层次顺序对类别的同时预测及其概念超类。我们在实验上证明，我们提出的网络可以同时预测粗大的超类和更好的类别，而不是多个数据集中的几种现有算法。
Classification is a pivotal function for many computer vision tasks such as object classification, detection, scene segmentation. Multinomial logistic regression with a single final layer of dense connections has become the ubiquitous technique for CNN-based classification. While these classifiers project a mapping between the input and a set of output category classes, they do not typically yield a comprehensive description of the category. In particular, when a CNN based image classifier correctly identifies the image of a Chimpanzee, its output does not clarify that Chimpanzee is a member of Primate, Mammal, Chordate families and a living thing. We propose a multilayer dense connectivity for concurrent prediction of category and its conceptual superclasses in hierarchical order by the same CNN. We experimentally demonstrate that our proposed network can simultaneously predict both the coarse superclasses and finer categories better than several existing algorithms in multiple datasets.
