通过非参数部件原型学习实现可解释图像分类
Interpretable Image Classification via Non-parametric Part Prototype Learning
AI总结：
本文提出非参数部件原型学习框架，通过聚类基础视觉模型的深度特征获得语义独特的部件原型，并以两项指标证明其在多个数据集上提升 ProtoPNets 的分类解释质量。
摘要：
以可解释的决策过程对图像进行分类是计算机视觉中一个长期存在的问题。近年来，Prototypical Part Networks（原型部件网络）作为一种自解释神经网络方法受到关注，因为它们能够通过提供基于原型对象部件的解释来模拟人类视觉推理。然而，这些方法生成的解释质量仍有提升空间，因为原型通常关注重复且冗余的概念。借助原型学习的最新进展，我们提出了一个基于部件的可解释图像分类框架，该框架为每个类别学习一组语义上具有区分性的对象部件，并提供多样且全面的解释。我们方法的核心是以非参数方式学习部件原型，具体做法是对从基础视觉模型中提取的深度特征进行聚类，这些特征编码了鲁棒的语义信息。为了定量评估 ProtoPNets 所提供解释的质量，我们引入了 Distinctiveness Score（区分性分数）和 Comprehensiveness Score（全面性分数）。通过在 CUB-200-2011、Stanford Cars 和 Stanford Dogs 数据集上的评估，我们表明，与现有 ProtoPNets 相比，我们的框架表现更优，同时实现了更好的可解释性。代码可在 https://github.com/zijizhu/proto-non-param 获取。
英文摘要：
Classifying images with an interpretable decision-making process is a long-standing problem in computer vision. In recent years, Prototypical Part Networks has gained traction as an approach for self-explainable neural networks, due to their ability to mimic human visual reasoning by providing explanations based on prototypical object parts. However, the quality of the explanations generated by these methods leaves room for improvement, as the prototypes usually focus on repetitive and redundant concepts. Leveraging recent advances in prototype learning, we present a framework for part-based interpretable image classification that learns a set of semantically distinctive object parts for each class, and provides diverse and comprehensive explanations. The core of our method is to learn the part-prototypes in a non-parametric fashion, through clustering deep features extracted from foundation vision models that encode robust semantic information. To quantitatively evaluate the quality of explanations provided by ProtoPNets, we introduce Distinctiveness Score and Comprehensiveness Score. Through evaluation on CUB-200-2011, Stanford Cars and Stanford Dogs datasets, we show that our framework compares favourably against existing ProtoPNets while achieving better interpretability. Code is available at: https://github.com/zijizhu/proto-non-param.
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。
