Prototypical parts networks combine the power of deep learning with the
explainability of case-based reasoning to make accurate, interpretable
decisions. They follow the this looks like that reasoning, representing each
prototypical part with patches from training images. However, a single image
patch comprises multiple visual features, such as color, shape, and texture,
making it difficult for users to identify which feature is important to the
model.
To reduce this ambiguity, we introduce the Lucid Prototypical Parts Network
(LucidPPN), a novel prototypical parts network that separates color prototypes
from other visual features. Our method employs two reasoning branches: one for
non-color visual features, processing grayscale images, and another focusing
solely on color information. This separation allows us to clarify whether the
model's decisions are based on color, shape, or texture. Additionally, LucidPPN
identifies prototypical parts corresponding to semantic parts of classified
objects, making comparisons between data classes more intuitive, e.g., when two
bird species might differ primarily in belly color.
Our experiments demonstrate that the two branches are complementary and
together achieve results comparable to baseline methods. More importantly,
LucidPPN generates less ambiguous prototypical parts, enhancing user
understanding.

使用深度学习与基于案例推理的权力，原型部分网络使决策准确且可解释，通过以训练图像的补丁表示每个原型部分，但单个图像补丁包含多个视觉特征，如颜色、形状和纹理，使用户难以确定模型重要的特征。为减少此模糊性，引入了 Lucid Prototypical Parts Network (LucidPPN), 一种新颖的原型部分网络，将颜色原型与其他视觉特征分离。我们的方法采用两个推理分支：一个用于非颜色视觉特征，处理灰度图像，另一个专注于颜色信息。通过此分离，我们可以澄清模型决策是基于颜色、形状还是纹理。此外，LucidPPN 识别对应于分类对象的语义部分的原型部分，使数据类之间的比较更加直观，例如，当两个鸟类主要在于腹部颜色不同时。我们的实验表明，这两个分支是互补的，并且共同实现了与基准方法相当的结果。更重要的是，LucidPPN 生成的原型部分模糊性较小，增强用户理解。