Diverse by Design: Architectural Constraints for Prototype-Based Interpretability

Diversity-Aware Prototype Learning (DAPL), a prototype-based neural network method that enforces prototype diversity through architectural constraints instead of explicit regularization, achieved 81.69% accuracy with 0.596 Coverage and 0.427 Diversity on CUB-200-2011, according to an arXiv paper (arXiv:2609.27194v1). DAPL uses multi-head self-attention with strict one-to-one attention-to-prototype mapping so each prototype specializes in distinct visual features, plus foreground-aware training and new Coverage and Diversity metrics for quantitative interpretability assessment. The authors report this as the best overall balance across all evaluated prototype-based methods, with code available at https://github.com/xinmiaolin/DAPL.

arXiv:2609.27194v1 Announce Type: new Abstract: 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.