# An Overview of Prototype Formulations for Interpretable Deep Learning

arXiv: https://arxiv.org/abs/2410.08925 · HTML: https://mlsanity.com/paper/2410.08925/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 11 Oct 2024.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions](https://mlsanity.com/paper/1710.04806/) (2017)
- [Neural Prototype Trees for Interpretable Fine-grained Image Recognition](https://mlsanity.com/paper/2012.02046/) (2020)
- [Rethinking Semantic Segmentation: A Prototype View](https://mlsanity.com/paper/2203.15102/) (2022)
- [Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes](https://mlsanity.com/paper/2111.15000/) (2021)
- [Interpretable Image Classification with Differentiable Prototypes Assignment](https://mlsanity.com/paper/2112.02902/) (2021)
- [Hyperspherical Prototype Networks](https://mlsanity.com/paper/1901.10514/) (2019)
- [ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition](https://mlsanity.com/paper/2208.10431/) (2022)
- [Learning Support and Trivial Prototypes for Interpretable Image Classification](https://mlsanity.com/paper/2301.04011/) (2023)
- [This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizations](https://mlsanity.com/paper/2310.18589/) (2023)
- [ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts](https://mlsanity.com/paper/2301.12276/) (2023)
- [Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanations](https://mlsanity.com/paper/2308.08162/) (2023)
- [MCPNet: An Interpretable Classifier via Multi-Level Concept Prototypes](https://mlsanity.com/paper/2404.08968/) (2024)
- [ProtoGMM: Multi-prototype Gaussian-Mixture-based Domain Adaptation Model for Semantic Segmentation](https://mlsanity.com/paper/2406.19225/) (2024)

## Built on by (most cited first, 5 of 5)

- [Interpretable Affordance Detection on 3D Point Clouds with Probabilistic Prototypes](https://mlsanity.com/paper/2504.18355/) (2025)
- [Interpretable 3D Neural Object Volumes for Robust Conceptual Reasoning](https://mlsanity.com/paper/2503.13429/) (2025)
- [Comprehensive Evaluation of Prototype Neural Networks](https://mlsanity.com/paper/2507.06819/) (2025)
- [ProtoSSL: Self-Supervised Pretraining and Downstream Transfer for Projection-Based Prototype Models](https://mlsanity.com/paper/2605.06943/) (2026)
- [Beyond L2: Generalizing Abductive Latent Explanations to Diverse Prototype-Based Architectures](https://mlsanity.com/paper/2608.16773/) (2026)

## Abstract (arXiv)

Prototypical part networks offer interpretable alternatives to black-box deep learning models by learning visual prototypes for classification. This work provides a comprehensive analysis of prototype formulations, comparing point-based and probabilistic approaches in both Euclidean and hyperspherical latent spaces. We introduce HyperPG, a probabilistic prototype representation using Gaussian distributions on hyperspheres. Experiments on CUB-200-2011, Stanford Cars, and Oxford Flowers datasets show that hyperspherical prototypes outperform standard Euclidean formulations. Critically, hyperspherical prototypes maintain competitive performance under simplified training schemes, while Euclidean prototypes require extensive hyperparameter tuning.