LucidPPN：面向用户可解释计算机视觉的无歧义原型部件网络
LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision
AI总结：
LucidPPN通过分离颜色与非颜色特征的原型部件网络，减少原型歧义，提升用户对模型决策的理解，且性能与基线相当。
摘要：
原型部件网络将深度学习的强大能力与基于案例推理的可解释性相结合，以做出准确、可解释的决策。它们遵循“这看起来像那”的推理方式，用训练图像中的补丁来表示每个原型部件。然而，单个图像补丁包含多种视觉特征，如颜色、形状和纹理，这使得用户难以识别哪个特征对模型重要。为减少这种歧义，我们引入了清晰原型部件网络（LucidPPN），一种新颖的原型部件网络，它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：一个处理灰度图像的非颜色视觉特征，另一个仅关注颜色信息。这种分离使我们能够澄清模型的决策是基于颜色、形状还是纹理。此外，LucidPPN识别对应于分类对象语义部分的原型部件，使数据类之间的比较更直观，例如，当两种鸟类可能主要区别在于腹部颜色时。我们的实验表明，这两个分支是互补的，共同实现的结果与基线方法相当。更重要的是，LucidPPN生成歧义更少的原型部件，增强了用户的理解。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
