论文标题
用于分层多标签图像分类的胶囊网络
A Capsule Network for Hierarchical Multi-Label Image Classification
论文作者
论文摘要
图像分类是计算机视觉中最重要的领域之一。当将多类图像分类问题基于层次结构或分类法排列为较小的图像分类问题时，将适用层次多标签分类。因此，分层分类模式通常在每个实例上提供多个类预测，从而期望这些模式反映图像类的结构相互关联。在本文中，我们提出了用于分层分类的多标签胶囊网络（ML-CAPSNET）。我们的ML-CAPSNET根据分层类标签树结构预测多个图像类。为此，我们提出了一个损失函数，该函数考虑了网络的多标签预测。结果，我们的ML-CapsNet的训练方法使用粗到细的范式，同时与标签层次结构中的分类水平保持一致。我们还使用广泛可用的数据集执行实验，并将模型与文献其他地方的替代方案进行比较。在我们的实验中，我们的ML capsnet在这些替代方法方面产生了改善的余地。
Image classification is one of the most important areas in computer vision. Hierarchical multi-label classification applies when a multi-class image classification problem is arranged into smaller ones based upon a hierarchy or taxonomy. Thus, hierarchical classification modes generally provide multiple class predictions on each instance, whereby these are expected to reflect the structure of image classes as related to one another. In this paper, we propose a multi-label capsule network (ML-CapsNet) for hierarchical classification. Our ML-CapsNet predicts multiple image classes based on a hierarchical class-label tree structure. To this end, we present a loss function that takes into account the multi-label predictions of the network. As a result, the training approach for our ML-CapsNet uses a coarse to fine paradigm while maintaining consistency with the structure in the classification levels in the label-hierarchy. We also perform experiments using widely available datasets and compare the model with alternatives elsewhere in the literature. In our experiments, our ML-CapsNet yields a margin of improvement with respect to these alternative methods.
