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.

翻译：原型部件网络通过学习视觉原型进行分类，为黑盒深度学习模型提供了可解释的替代方案。本文对原型表示方法进行了全面分析，比较了欧几里得空间与超球面潜在空间中基于点的方法与概率方法的差异。我们提出了HyperPG，一种在超球面上使用高斯分布的概率原型表示方法。在CUB-200-2011、Stanford Cars和Oxford Flowers数据集上的实验表明，超球面原型优于标准欧几里得表示。关键的是，超球面原型在简化训练方案下仍能保持竞争力，而欧几里得原型则需要大量超参数调优。