# Diverse by Design: Architectural Constraints for Prototype-Based Interpretability

arXiv: https://arxiv.org/abs/2609.27194 · HTML: https://mlsanity.com/paper/2609.27194/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 23 Sep 2026.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (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)
- [ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discovery](https://mlsanity.com/paper/2011.14340/) (2020)
- [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)
- [Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networks](https://mlsanity.com/paper/2212.05946/) (2022)
- [This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizations](https://mlsanity.com/paper/2310.18589/) (2023)
- [LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity](https://mlsanity.com/paper/2404.03214/) (2024)
- [Interpretable Image Classification with Adaptive Prototype-based Vision Transformers](https://mlsanity.com/paper/2410.20722/) (2024)
- [ProtoMIL: Multiple Instance Learning with Prototypical Parts for Whole-Slide Image Classification](https://mlsanity.com/paper/2108.10612/) (2021)
- [Pixel-Grounded Prototypical Part Networks](https://mlsanity.com/paper/2309.14531/) (2023)
- [LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision](https://mlsanity.com/paper/2405.14331/) (2024)
- [Attention (as Discrete-Time Markov) Chains](https://mlsanity.com/paper/2507.17657/) (2025)
- [Gradient Frequency Modulation for Visually Explaining Video Understanding Models](https://mlsanity.com/paper/2111.01215/) (2021)
- [On Model Explanations with Transferable Neural Pathways](https://mlsanity.com/paper/2309.09887/) (2023)
- [ProtoSolo: Interpretable Image Classification via Single-Prototype Activation](https://mlsanity.com/paper/2506.19808/) (2025)

## Abstract (arXiv)

Prototype-based neural networks provide inherent interpretability through case-based reasoning, yet suffer from critical limitations: prototypes converge to redundant features, fail to capture diverse semantic parts, and lack quantitative interpretability assessment. We propose Diversity-Aware Prototype Learning (DAPL), which enforces prototype diversity through architectural constraints rather than explicit regularization. Our approach leverages multi-head self-attention with strict one-to-one attention-to-prototype mapping, ensuring each prototype specializes in distinct visual features. We further introduce foreground-aware training to focus prototypes on semantically meaningful regions and develop comprehensive evaluation metrics (Coverage and Diversity) for quantitative interpretability assessment. Experiments on CUB-200-2011 demonstrate substantial improvements: DAPL with foreground-aware training achieves 81.69% accuracy with 0.596 Coverage and 0.427 Diversity, providing the best overall balance across all evaluated prototype-based methods. Code is available at https://github.com/xinmiaolin/DAPL.