Hierarchical Transformers for Unsupervised 3D Shape Abstraction

• URL: http://arxiv.org/abs/2510.27088v1
• Date: Fri, 31 Oct 2025 01:19:05 GMT
• Title: Hierarchical Transformers for Unsupervised 3D Shape Abstraction
• Authors: Aditya Vora, Lily Goli, Andrea Tagliasacchi, Hao Zhang,
• Abstract summary: We introduce HiT, a novel hierarchical neural field representation for 3D shapes.<n>HiT learns general hierarchies in a coarse-to-fine manner across different shape categories in an unsupervised setting.<n>We demonstrate its effectiveness through an unsupervised shape segmentation task over all 55 ShapeNet categories.
• Score: 29.488408094629545
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce HiT, a novel hierarchical neural field representation for 3D shapes that learns general hierarchies in a coarse-to-fine manner across different shape categories in an unsupervised setting. Our key contribution is a hierarchical transformer (HiT), where each level learns parent-child relationships of the tree hierarchy using a compressed codebook. This codebook enables the network to automatically identify common substructures across potentially diverse shape categories. Unlike previous works that constrain the task to a fixed hierarchical structure (e.g., binary), we impose no such restriction, except for limiting the total number of nodes at each tree level. This flexibility allows our method to infer the hierarchical structure directly from data, over multiple shape categories, and representing more general and complex hierarchies than prior approaches. When trained at scale with a reconstruction loss, our model captures meaningful containment relationships between parent and child nodes. We demonstrate its effectiveness through an unsupervised shape segmentation task over all 55 ShapeNet categories, where our method successfully segments shapes into multiple levels of granularity.

Related papers

• Provable Learning of Random Hierarchy Models and Hierarchical Shallow-to-Deep Chaining [58.69016084278948]
  We consider a hierarchical context-free grammar introduced by arXiv:2307.02129 and conjectured to separate deep and shallow networks.<n>We prove that, under mild conditions, a deep convolutional network can be efficiently trained to learn this function class.
  arXiv  Detail & Related papers  (2026-01-27T16:19:54Z)
• The Geometry of Meaning: Perfect Spacetime Representations of Hierarchical Structures [0.0]
  We show that there is a fast algorithm that embeds hierarchical structures in three-dimensional Minkowski spacetime.<n>Our results seem to indicate that all discrete data has a perfect geometrical representation that is three-dimensional.
  arXiv  Detail & Related papers  (2025-05-07T20:41:06Z)
• Learning and Evaluating Hierarchical Feature Representations [3.770103075126785]
  We propose a novel framework, Hierarchical Composition of Orthogonal Subspaces (Hier-COS)<n>Hier-COS learns to map deep feature embeddings into a vector space that is, by design, consistent with the structure of a given taxonomy tree.<n>We demonstrate that Hier-COS achieves state-of-the-art hierarchical performance across all the datasets while simultaneously beating top-1 accuracy in all but one case.
  arXiv  Detail & Related papers  (2025-03-10T20:59:41Z)
• StructRe: Rewriting for Structured Shape Modeling [60.20359722058389]
  We present StructRe, a structure rewriting system, as a novel approach to structured shape modeling.<n>Given a 3D object represented by points and components, StructRe can rewrite it upward into more concise structures, or downward into more detailed structures.
  arXiv  Detail & Related papers  (2023-11-29T10:35:00Z)
• How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model [47.617093812158366]
  We introduce the Random Hierarchy Model: a family of synthetic tasks inspired by the hierarchical structure of language and images. We find that deep networks learn the task by developing internal representations invariant to exchanging equivalent groups. Our results indicate how deep networks overcome the curse of dimensionality by building invariant representations.
  arXiv  Detail & Related papers  (2023-07-05T09:11:09Z)
• Hierarchical clustering with dot products recovers hidden tree structure [53.68551192799585]
  In this paper we offer a new perspective on the well established agglomerative clustering algorithm, focusing on recovery of hierarchical structure. We recommend a simple variant of the standard algorithm, in which clusters are merged by maximum average dot product and not, for example, by minimum distance or within-cluster variance. We demonstrate that the tree output by this algorithm provides a bona fide estimate of generative hierarchical structure in data, under a generic probabilistic graphical model.
  arXiv  Detail & Related papers  (2023-05-24T11:05:12Z)
• Implant Global and Local Hierarchy Information to Sequence based Code Representation Models [25.776540440893257]
  We analyze how the complete hierarchical structure influences the tokens in code sequences and abstract this influence as a property of code tokens called hierarchical embedding. We propose the Hierarchy Transformer (HiT), a simple but effective sequence model to incorporate the complete hierarchical embeddings of source code into a Transformer model.
  arXiv  Detail & Related papers  (2023-03-14T12:01:39Z)
• Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework [75.79736930414715]
  We present a hierarchical multi-label representation learning framework that can leverage all available labels and preserve the hierarchical relationship between classes. We introduce novel hierarchy preserving losses, which jointly apply a hierarchical penalty to the contrastive loss, and enforce the hierarchy constraint.
  arXiv  Detail & Related papers  (2022-04-27T21:41:44Z)
• RIM-Net: Recursive Implicit Fields for Unsupervised Learning of Hierarchical Shape Structures [18.5420635041504]
  RIM-Net is a neural network which learns implicit fields for unsupervised inference of hierarchical shape structures. We show the quality, consistency, and interpretability of hierarchical structural inference by RIM-Net.
  arXiv  Detail & Related papers  (2022-01-30T09:31:24Z)
• Label Hierarchy Transition: Delving into Class Hierarchies to Enhance Deep Classifiers [40.993137740456014]
  We propose a unified probabilistic framework based on deep learning to address the challenges of hierarchical classification. The proposed framework can be readily adapted to any existing deep network with only minor modifications. We extend our proposed LHT framework to the skin lesion diagnosis task and validate its great potential in computer-aided diagnosis.
  arXiv  Detail & Related papers  (2021-12-04T14:58:36Z)
• Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones [64.75766944882389]
  We present ConE (Cone Embedding), a KG embedding model that is able to simultaneously model multiple hierarchical as well as non-hierarchical relations in a knowledge graph. In particular, ConE uses cone containment constraints in different subspaces of the hyperbolic embedding space to capture multiple heterogeneous hierarchies. Our approach yields new state-of-the-art Hits@1 of 45.3% on WN18RR and 16.1% on DDB14 (0.231 MRR)
  arXiv  Detail & Related papers  (2021-10-28T07:16:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.