# Leveraging Class Hierarchies with Metric-Guided Prototype Learning

arXiv: https://arxiv.org/abs/2007.03047 · HTML: https://mlsanity.com/paper/2007.03047/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2020.

## Built on by (most cited first, 20 of 20)

- [Deep Hierarchical Semantic Segmentation](https://mlsanity.com/paper/2203.14335/) (2022)
- [Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework](https://mlsanity.com/paper/2204.13207/) (2022)
- [Learning Hierarchy Aware Features for Reducing Mistake Severity](https://mlsanity.com/paper/2207.12646/) (2022)
- [Skin Lesion Recognition with Class-Hierarchy Regularized Hyperbolic Embeddings](https://mlsanity.com/paper/2209.05842/) (2022)
- [TransHP: Image Classification with Hierarchical Prompting](https://mlsanity.com/paper/2304.06385/) (2023)
- [Visually Consistent Hierarchical Image Classification](https://mlsanity.com/paper/2406.11608/) (2024)
- [Online Continual Learning on Hierarchical Label Expansion](https://mlsanity.com/paper/2308.14374/) (2023)
- [HIERMATCH: Leveraging Label Hierarchies for Improving Semi-Supervised Learning](https://mlsanity.com/paper/2111.00164/) (2021)
- [SEAL: Simultaneous Label Hierarchy Exploration And Learning](https://mlsanity.com/paper/2304.13374/) (2023)
- [FLAIR-HUB: Large-scale Multimodal Dataset for Land Cover and Crop Mapping](https://mlsanity.com/paper/2506.07080/) (2025)
- [Test-Time Amendment with a Coarse Classifier for Fine-Grained Classification](https://mlsanity.com/paper/2302.00368/) (2023)
- [Prototype Based Classification from Hierarchy to Fairness](https://mlsanity.com/paper/2205.13997/) (2022)
- [United We Learn Better: Harvesting Learning Improvements From Class Hierarchies Across Tasks](https://mlsanity.com/paper/2107.13627/) (2021)
- [All Mistakes Are Not Equal: Comprehensive Hierarchy Aware Multi-label Predictions (CHAMP)](https://mlsanity.com/paper/2206.08653/) (2022)
- [Inspecting class hierarchies in classification-based metric learning models](https://mlsanity.com/paper/2301.11065/) (2023)
- [Multi-level Supervised Contrastive Learning](https://mlsanity.com/paper/2502.02202/) (2025)
- [Introducing the structural bases of typicality effects in deep learning](https://mlsanity.com/paper/2107.03279/) (2021)
- [Hier-COS: Making Deep Features Hierarchy-aware via Composition of Orthogonal Subspaces](https://mlsanity.com/paper/2503.07853/) (2025)
- [T3S: Think in Thermal Time for Generalizable Crop Mapping from Satellite Image Time Series](https://mlsanity.com/paper/2506.12885/) (2025)
- [Feature Identification for Hierarchical Contrastive Learning](https://mlsanity.com/paper/2510.00837/) (2025)

## Abstract (arXiv)

In many classification tasks, the set of target classes can be organized into a hierarchy. This structure induces a semantic distance between classes, and can be summarised under the form of a cost matrix, which defines a finite metric on the class set. In this paper, we propose to model the hierarchical class structure by integrating this metric in the supervision of a prototypical network. Our method relies on jointly learning a feature-extracting network and a set of class prototypes whose relative arrangement in the embedding space follows an hierarchical metric. We show that this approach allows for a consistent improvement of the error rate weighted by the cost matrix when compared to traditional methods and other prototype-based strategies. Furthermore, when the induced metric contains insight on the data structure, our method improves the overall precision as well. Experiments on four different public datasets - from agricultural time series classification to depth image semantic segmentation - validate our approach.