多样性的设计：基于原型的可解释性的架构约束
Diverse by Design: Architectural Constraints for Prototype-Based Interpretability
- Rochester Institute of Technology（罗切斯特理工学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对基于原型的神经网络原型冗余、缺乏多样性和定量评估的问题，提出DAPL，通过架构约束和前景感知训练提升原型多样性，在CUB-200-2011上以81.69%准确率实现最佳平衡。
AI中文摘要：
基于原型的神经网络通过基于案例的推理提供了固有的可解释性，但存在关键局限性：原型收敛到冗余特征，无法捕获多样的语义部分，并且缺乏定量的可解释性评估。我们提出了多样性感知的原型学习（DAPL），通过架构约束而非显式正则化来强制实现原型多样性。我们的方法利用多头自注意力，并严格采用一对一的注意力到原型的映射，确保每个原型专注于不同的视觉特征。我们进一步引入前景感知训练，使原型聚焦于语义上有意义的区域，并开发了全面的评估指标（覆盖率和多样性）用于定量可解释性评估。在CUB-200-2011上的实验展示了显著改进：具有前景感知训练的DAPL达到了81.69%的准确率，覆盖率为0.596，多样性为0.427，在所有评估的基于原型的方法中提供了最佳的整体平衡。代码可在https://github.com/xinmiaolin/DAPL获取。
英文摘要：
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.
