MCPNet：一种基于多级概念原型的可解释分类器
MCPNet: An Interpretable Classifier via Multi-Level Concept Prototypes
AI总结：
提出内在可解释模型MCPNet，利用CKA损失和能量加权PCA机制自主跨多级特征图学习概念原型，并通过CCD损失对齐原型分布进行分类，在保持准确率的同时提供全面多级解释并提升少样本泛化能力。
摘要：
事后和内在可解释方法的最新进展显著增强了对黑盒分类器模型的解释能力。这些方法要么通过事后分析进行，要么在模型训练期间整合概念学习。尽管在弥合模型潜在空间与人类解释之间的语义鸿沟方面很有效，但这些解释方法仅部分揭示了模型的决策过程。其结果通常局限于从最后一个特征图得出的高级语义。我们认为，缺乏对低级和中级特征决策过程洞察的解释既不完全可信，也不完全有用。为了解决这一差距，我们引入了多级概念原型分类器（MCPNet），这是一种内在可解释模型。MCPNet利用中心核对齐（CKA）损失和基于能量的加权PCA机制，自主跨多个特征图级别学习有意义的概念原型，且无需依赖预定义的概念标签。此外，我们提出了一种新颖的分类器范式，通过类感知概念分布（CCD）损失学习和对齐多级概念原型分布以进行分类。我们的实验表明，我们提出的MCPNet在适应各种模型架构的同时，提供了全面的多级解释并保持了分类准确率。此外，其基于概念分布的分类方法在少样本分类场景中展现出更强的泛化能力。
英文摘要：
Recent advancements in post-hoc and inherently interpretable methods have markedly enhanced the explanations of black box classifier models. These methods operate either through post-analysis or by integrating concept learning during model training. Although being effective in bridging the semantic gap between a model's latent space and human interpretation, these explanation methods only partially reveal the model's decision-making process. The outcome is typically limited to high-level semantics derived from the last feature map. We argue that the explanations lacking insights into the decision processes at low and mid-level features are neither fully faithful nor useful. Addressing this gap, we introduce the Multi-Level Concept Prototypes Classifier (MCPNet), an inherently interpretable model. MCPNet autonomously learns meaningful concept prototypes across multiple feature map levels using Centered Kernel Alignment (CKA) loss and an energy-based weighted PCA mechanism, and it does so without reliance on predefined concept labels. Further, we propose a novel classifier paradigm that learns and aligns multi-level concept prototype distributions for classification purposes via Class-aware Concept Distribution (CCD) loss. Our experiments reveal that our proposed MCPNet while being adaptable to various model architectures, offers comprehensive multi-level explanations while maintaining classification accuracy. Additionally, its concept distribution-based classification approach shows improved generalization capabilities in few-shot classification scenarios.
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。
