ProtoArgNet：基于超级原型和论证的可解释图像分类 [技术报告]
ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation [Technical Report]
AI总结：
本文提出ProtoArgNet可解释图像分类架构，通过超级原型组合原型部分并利用论证提供支持/攻击解释，在多个数据集上优于现有原型部分学习方法，且论证组件可定制以生成更简洁解释。
摘要：
我们提出ProtoArgNet，这是一种新颖的可解释深度神经架构，用于图像分类，其理念源于原型部分学习，例如在ProtoPNet中所见。早期方法将每个类别与多个原型部分相关联，而ProtoArgNet使用超级原型将原型部分组合成统一的类别表示。这通过以类似MLP的方式组合原型的局部激活来实现，从而能够定位原型并学习它们之间的（非线性）空间关系。通过利用一种论证形式，ProtoArgNet能够提供支持性（即‘这看起来像那’）和攻击性（即‘这与那不同’）两种解释。我们在多个数据集上证明，ProtoArgNet优于最先进的原型部分学习方法。此外，ProtoArgNet中的论证组件可通过稀疏化过程根据用户的认知需求进行定制，与最先进的方法相比，这会产生更简洁的解释。
英文摘要：
We propose ProtoArgNet, a novel interpretable deep neural architecture for image classification in the spirit of prototypical-part-learning as found, e.g., in ProtoPNet. While earlier approaches associate every class with multiple prototypical-parts, ProtoArgNet uses super-prototypes that combine prototypical-parts into a unified class representation. This is done by combining local activations of prototypes in an MLP-like manner, enabling the localization of prototypes and learning (non-linear) spatial relationships among them. By leveraging a form of argumentation, ProtoArgNet is capable of providing both supporting (i.e. `this looks like that') and attacking (i.e. `this differs from that') explanations. We demonstrate on several datasets that ProtoArgNet outperforms state-of-the-art prototypical-part-learning approaches. Moreover, the argumentation component in ProtoArgNet is customisable to the user's cognitive requirements by a process of sparsification, which leads to more compact explanations compared to state-of-the-art approaches.
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。
