This work investigates how hierarchically structured data can help neural
networks learn conceptual representations of cathedrals. The underlying
WikiScenes dataset provides a spatially organized hierarchical structure of
cathedral components. We propose a novel hierarchical contrastive training
approach that leverages a triplet margin loss to represent the data's spatial
hierarchy in the encoder's latent space. As such, the proposed approach
investigates if the dataset structure provides valuable information for
self-supervised learning. We apply t-SNE to visualize the resultant latent
space and evaluate the proposed approach by comparing it with other
dataset-specific contrastive learning methods using a common downstream
classification task. The proposed method outperforms the comparable
weakly-supervised and baseline methods. Our findings suggest that dataset
structure is a valuable modality for weakly-supervised learning.

本研究探讨了如何使用分层结构化数据来帮助神经网络学习大教堂的概念表示。通过 WikiScenes 数据集提供的空间组织的分层结构，我们提出了一种新颖的分层对比训练方法，利用三元组边界损失在编码器的潜在空间中表示数据的空间层次结构，研究了数据集结构是否为自监督学习提供了有价值的信息。通过应用 t-SNE 可视化所得到的潜在空间并将所提出的方法与其他具有特定数据集的对比学习方法在常见的下游分类任务中进行比较评估，结果表明所提方法优于可比较的弱监督和基准方法。我们的发现表明数据集结构是弱监督学习中有价值的模态。