Deep Taxonomic Networks for Unsupervised Hierarchical Prototype Discovery
Preprint
Abstract
Inspired by the human ability to learn and organize knowledge into hierarchical taxonomies with prototypes, this paper addresses key limitations in current deep hierarchical clustering methods. Existing methods often tie the structure to the number of classes and underutilize the rich prototype information available at intermediate hierarchical levels. We introduce deep taxonomic networks, a novel deep latent variable approach designed to bridge these gaps. Our method optimizes a large latent taxonomic hierarchy, specifically a complete binary tree structured mixture-of-Gaussian prior within a variational inference framework, to automatically discover taxonomic structures and associated prototype clusters directly from unlabeled data without assuming true label sizes. We analytically show that optimizing the ELBO of our method encourages the discovery of hierarchical relationships among prototypes. Empirically, our learned models demonstrate strong hierarchical clustering performance, outperforming baselines across diverse image classification datasets using our novel evaluation mechanism that leverages prototype clusters discovered at all hierarchical levels. Qualitative results further reveal that deep taxonomic networks discover rich and interpretable hierarchical taxonomies, capturing both coarse-grained semantic categories and fine-grained visual distinctions.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- DeepECT: The Deep Embedded Cluster TreeData Science and Engineering, 2020
- Evolution of Active Categorical Image Classification via Saccadic Eye MovementLecture Notes in Computer Science, 2016
- Deep Residual Learning for Image Recognition2016
- How to Grow a Mind: Statistics, Structure, and AbstractionScience, 2011
- Cobweb Models of Categorization and Probabilistic Concept Formation2011
- The development of object categorization in young children: Hierarchical inclusiveness, age, perceptual attribute, and group versus individual analyses.Developmental Psychology, 2010
- Labels as Features (Not Names) for Infant Categorization: A Neurocomputational ApproachCognitive Science, 2009
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Conceptual Clustering, Learning from Examples, and Inference1987
- Hierarchical Grouping to Optimize an Objective FunctionJournal of the American Statistical Association, 1963