Prototype Learning methods provide an interpretable alternative to black-box deep learning models. Approaches such as ProtoPNet learn, which part of a test image "look like" known prototypical parts from training images, combining predictive power with the inherent interpretability of case-based reasoning. However, existing approaches have two main drawbacks: A) They rely solely on deterministic similarity scores without statistical confidence. B) The prototypes are learned in a black-box manner without human input. This work introduces HyperPg, a new prototype representation leveraging Gaussian distributions on a hypersphere in latent space, with learnable mean and variance. HyperPg prototypes adapt to the spread of clusters in the latent space and output likelihood scores. The new architecture, HyperPgNet, leverages HyperPg to learn prototypes aligned with human concepts from pixel-level annotations. Consequently, each prototype represents a specific concept such as color, image texture, or part of the image subject. A concept extraction pipeline built on foundation models provides pixel-level annotations, significantly reducing human labeling effort. Experiments on CUB-200-2011 and Stanford Cars datasets demonstrate that HyperPgNet outperforms other prototype learning architectures while using fewer parameters and training steps. Additionally, the concept-aligned HyperPg prototypes are learned transparently, enhancing model interpretability.

翻译：原型学习方法为黑盒深度学习模型提供了一种可解释的替代方案。诸如ProtoPNet等方法通过学习测试图像的哪些部分“看起来像”训练图像中已知的原型部分，将预测能力与基于案例推理的固有可解释性相结合。然而，现有方法存在两个主要缺点：A) 它们仅依赖确定性相似度评分，缺乏统计置信度。B) 原型以黑盒方式学习，未融入人类先验知识。本文提出HyperPg，一种利用潜在空间超球面上高斯分布的新型原型表示方法，其均值和方差可学习。HyperPg原型能够适应潜在空间中簇的分布并输出似然分数。新架构HyperPgNet利用HyperPg学习与人类概念对齐的原型，这些概念源自像素级标注。因此，每个原型代表一个特定概念，例如颜色、图像纹理或图像主体的某部分。基于基础模型构建的概念提取流程可提供像素级标注，显著减少了人工标注工作量。在CUB-200-2011和Stanford Cars数据集上的实验表明，HyperPgNet在使用更少参数和训练步骤的同时，性能优于其他原型学习架构。此外，与概念对齐的HyperPg原型以透明方式学习，增强了模型的可解释性。