# Learning Hierarchical Visual Representations in Deep Neural Networks Using Hierarchical Linguistic Labels

arXiv: https://arxiv.org/abs/1805.07647 · HTML: https://mlsanity.com/paper/1805.07647/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2018.

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

- [A Survey of Neural Trees](https://mlsanity.com/paper/2209.03415/) (2022)
- [Extremely coarse learning objectives induce human-aligned representations in AI vision models](https://mlsanity.com/paper/2605.05556/) (2026)
- [Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style Classification](https://mlsanity.com/paper/2507.23436/) (2025)
- [Hierarchical Scaffolding Enables Human-Like Cognitive Selectivity under Data Scarcity](https://mlsanity.com/paper/2607.04709/) (2026)

## Abstract (arXiv)

Modern convolutional neural networks (CNNs) are able to achieve human-level object classification accuracy on specific tasks, and currently outperform competing models in explaining complex human visual representations. However, the categorization problem is posed differently for these networks than for humans: the accuracy of these networks is evaluated by their ability to identify single labels assigned to each image. These labels often cut arbitrarily across natural psychological taxonomies (e.g., dogs are separated into breeds, but never jointly categorized as "dogs"), and bias the resulting representations. By contrast, it is common for children to hear both "dog" and "Dalmatian" to describe the same stimulus, helping to group perceptually disparate objects (e.g., breeds) into a common mental class. In this work, we train CNN classifiers with multiple labels for each image that correspond to different levels of abstraction, and use this framework to reproduce classic patterns that appear in human generalization behavior.