论文标题
ProtopShare：可解释的图像分类和相似性发现的原型共享
ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discovery
论文作者
论文摘要
在本文中，我们介绍了ProtopShare，这是一种自我解释的方法，它结合了原型部分的范式来解释其预测。 Protopshare的主要新颖性是由于我们的数据依赖于数据的合并，其在类之间有效共享原型部分的能力。此外，原型更一致，模型比最先进的方法Protopnet的状态更适合图像扰动。我们在两个数据集（CUB-200-2011和Stanford Cars）上验证了我们的发现。
In this paper, we introduce ProtoPShare, a self-explained method that incorporates the paradigm of prototypical parts to explain its predictions. The main novelty of the ProtoPShare is its ability to efficiently share prototypical parts between the classes thanks to our data-dependent merge-pruning. Moreover, the prototypes are more consistent and the model is more robust to image perturbations than the state of the art method ProtoPNet. We verify our findings on two datasets, the CUB-200-2011 and the Stanford Cars.
