The inherent structure of human cognition facilitates the hierarchical organization of semantic categories for three-dimensional objects, simplifying the visual world into distinct and manageable layers. A vivid example is observed in the animal-taxonomy domain, where distinctions are not only made between broader categories like birds and mammals but also within subcategories such as different bird species, illustrating the depth of human hierarchical processing. This paper presents Deep Hierarchical Learning (DHL) on 3D data, a framework that, by formulating a probabilistic representation of hierarchical learning, lays down a pioneering theoretical foundation for hierarchical learning (HL) in 3D vision tasks. On this groundwork, we technically solve three primary challenges: 1) To effectively connect hierarchical coherence with classification loss, we introduce a hierarchical regularization term, utilizing an aggregation matrix from the forecasting field. 2) To align point-wise embeddings with hierarchical relationships, we develop the Hierarchical Embedding Fusion Module (HEFM) as a plug-in module in 3D deep learning, catalyzing enhanced hierarchical embedding learning. 3) To tackle the universality issue within DHL, we devise a novel method for constructing class hierarchies in common datasets with flattened fine-grained labels, employing large vision language models. The above approaches ensure the effectiveness of DHL in processing 3D data across multiple hierarchical levels. Through extensive experiments on three public datasets, the validity of our methodology is demonstrated. The source code will be released publicly, promoting further investigation and development in hierarchical learning.
- [2023/11/29] Official repo is created, code will be released soon, access our Project Page for more details.
This repository will be maintained by Yuheng. For any issues regarding code, dataset downloads, or the official website, you can contact Yuheng at the following email addresses: sc20yl2@leeds.ac.uk & yuhengliu02@gmail.com.