# Deep Taxonomic Networks for Unsupervised Hierarchical Prototype Discovery

arXiv: https://arxiv.org/abs/2509.23602 · HTML: https://mlsanity.com/paper/2509.23602/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 46 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Improving Variational Inference with Inverse Autoregressive Flow](https://mlsanity.com/paper/1606.04934/) (2016)
- [NVAE: A Deep Hierarchical Variational Autoencoder](https://mlsanity.com/paper/2007.03898/) (2020)
- [Opening the Black Box of Deep Neural Networks via Information](https://mlsanity.com/paper/1703.00810/) (2017)
- [Ladder Variational Autoencoders](https://mlsanity.com/paper/1602.02282/) (2016)
- [Contrastive Clustering](https://mlsanity.com/paper/2009.09687/) (2020)
- [Distilling a Neural Network Into a Soft Decision Tree](https://mlsanity.com/paper/1711.09784/) (2017)
- [Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering](https://mlsanity.com/paper/1611.05148/) (2016)
- [BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling](https://mlsanity.com/paper/1902.02102/) (2019)
- [LassoNet: A Neural Network with Feature Sparsity](https://mlsanity.com/paper/1907.12207/) (2019)
- [Multi-Facet Clustering Variational Autoencoders](https://mlsanity.com/paper/2106.05241/) (2021)
- [Nonparametric Variational Auto-encoders for Hierarchical Representation Learning](https://mlsanity.com/paper/1703.07027/) (2017)
- [Convolutional Cobweb: A Model of Incremental Learning from 2D Images](https://mlsanity.com/paper/2201.06740/) (2022)
- [Incremental Concept Formation over Visual Images Without Catastrophic Forgetting](https://mlsanity.com/paper/2402.16933/) (2024)
- [Hierarchically Clustered Representation Learning](https://mlsanity.com/paper/1901.09906/) (2019)
- [Cobweb: An Incremental and Hierarchical Model of Human-Like Category Learning](https://mlsanity.com/paper/2403.03835/) (2024)
- [From Logits to Hierarchies: Hierarchical Clustering made Simple](https://mlsanity.com/paper/2410.07858/) (2024)
- [Evolution of active categorical image classification via saccadic eye movement](https://mlsanity.com/paper/1603.08233/) (2016)

## Built on by (most cited first, 4 of 4)

- [Test-Time Compositional Generalization in Diffusion Models via Concept Discovery](https://mlsanity.com/paper/2605.07078/) (2026)
- [Classification Fields: Arbitrarily Fine Recursive Hierarchical Clustering From Few Examples](https://mlsanity.com/paper/2605.07119/) (2026)
- [Diffusion Models and Concept Formation](https://mlsanity.com/paper/2609.13047/) (2026)
- [DeepTopoClustering: Unsupervised Derivation of Surface Process Taxonomy from 4D Point Clouds for Topographic Monitoring](https://mlsanity.com/paper/2610.09860/) (2026)

## Abstract (arXiv)

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.