Deformable ProtoPNet：一种使用可变形原型的可解释图像分类器
Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes
AI总结：
本文提出Deformable ProtoPNet，通过引入空间灵活的可变形原型部件来捕捉姿态变化和上下文，在保持基于案例推理可解释性的同时提升了图像分类准确性和解释丰富性。
摘要：
我们提出了一种可变形原型部件网络（Deformable ProtoPNet），这是一种可解释的图像分类器，融合了深度学习的能力和基于案例推理的可解释性。该模型通过将输入图像与训练过程中学习到的原型进行比较来进行分类，从而产生“这个看起来像那个”形式的解释。然而，以往的方法使用空间上刚性的原型，我们通过提出空间上灵活的原型来解决这一不足。每个原型由若干个原型部件组成，这些部件根据输入图像自适应地改变它们的相对空间位置。因此，Deformable ProtoPNet 能够显式地捕捉姿态变化和上下文信息，同时提高模型准确性和所提供解释的丰富性。与其他使用原型的基于案例的可解释模型相比，我们的方法达到了最先进的准确性，并提供了具有更丰富上下文的解释。代码可在 https://github.com/jdonnelly36/Deformable-ProtoPNet 获取。
英文摘要：
We present a deformable prototypical part network (Deformable ProtoPNet), an interpretable image classifier that integrates the power of deep learning and the interpretability of case-based reasoning. This model classifies input images by comparing them with prototypes learned during training, yielding explanations in the form of "this looks like that." However, while previous methods use spatially rigid prototypes, we address this shortcoming by proposing spatially flexible prototypes. Each prototype is made up of several prototypical parts that adaptively change their relative spatial positions depending on the input image. Consequently, a Deformable ProtoPNet can explicitly capture pose variations and context, improving both model accuracy and the richness of explanations provided. Compared to other case-based interpretable models using prototypes, our approach achieves state-of-the-art accuracy and gives an explanation with greater context. The code is available at https://github.com/jdonnelly36/Deformable-ProtoPNet.
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。
