Prototypical part network (ProtoPNet) methods have been designed to achieve interpretable classification by associating predictions with a set of training prototypes, which we refer to as trivial prototypes because they are trained to lie far from the classification boundary in the feature space. Note that it is possible to make an analogy between ProtoPNet and support vector machine (SVM) given that the classification from both methods relies on computing similarity with a set of training points (i.e., trivial prototypes in ProtoPNet, and support vectors in SVM). However, while trivial prototypes are located far from the classification boundary, support vectors are located close to this boundary, and we argue that this discrepancy with the well-established SVM theory can result in ProtoPNet models with inferior classification accuracy. In this paper, we aim to improve the classification of ProtoPNet with a new method to learn support prototypes that lie near the classification boundary in the feature space, as suggested by the SVM theory. In addition, we target the improvement of classification results with a new model, named ST-ProtoPNet, which exploits our support prototypes and the trivial prototypes to provide more effective classification. Experimental results on CUB-200-2011, Stanford Cars, and Stanford Dogs datasets demonstrate that ST-ProtoPNet achieves state-of-the-art classification accuracy and interpretability results. We also show that the proposed support prototypes tend to be better localised in the object of interest rather than in the background region.
翻译:原始部分网络(ProtoPNet)方法的设计是为了实现可解释的分类,方法是将预测与一套培训原型联系起来,我们称之为微不足道的原型原型,因为经过培训,它们远离地貌空间的分类界限。请注意,可以将ProtoPNet与辅助矢量机(SVM)进行类比,因为两种方法的分类都依赖于与一套培训点(即ProtoPNet的微小原型,支持SVM的原型)的计算相似性。然而,虽然微小原型离分类界限很远,但支持性原型离这个边界很近,支持性矢量的原型离我们很近,而我们争辩说,与成熟的SVM理论的这一差异可能导致IPNet模型的分类精确性差,而分类精确性更差。在本文件中,我们的目标是改进ProtoPNet的分类,按照SVM理论,学习位于地段空间分类界限附近的支持原型。此外,我们的目标是改进分类结果的改进,用一个新的模型,即ST-ProtoPNet,在SAR-Stability 和SDISIS-SDBADVA 上,从而展示我们的SBA-C-C-C-C-C-C-C-C-C-C-C-C-Starstal-C-C-C-C-C-SLADIS-C-C-C-C-C-C-C-SLADIS-C-C-C-SAR-SDIS-SAR-SDIS 的原型数据。</s>