ProtoSolo：通过单原型激活实现可解释图像分类
ProtoSolo: Interpretable Image Classification via Single-Prototype Activation
AI总结：
针对可解释原型网络多原型决策认知复杂度高的问题，提出仅需单原型激活的ProtoSolo架构，结合特征图比对与非投影学习策略，在保持分类准确率的同时降低了认知复杂度。
摘要：
尽管可解释原型网络提升了深度学习图像分类的透明度，但多原型协同决策的需求增加了认知复杂度，阻碍了用户理解。为解决该问题，本文提出一种新型可解释图像分类深度架构ProtoSolo。与现有原型网络不同，ProtoSolo仅需激活单个原型即可完成分类。该设计大幅简化了解释过程，因为每个类别的解释只需展示相似度得分最高的原型及其对应特征图。此外，研究用特征图替代传统全通道特征向量进行相似度比较与原型学习，使单原型激活决策能够利用更丰富的全局信息。本文还引入了非投影原型学习策略，在保留原型与图像块关联的同时，避免投影导致的网络结构突变影响分类性能。在CUB-200-2011和Stanford Cars数据集上的实验表明，ProtoSolo在分类准确率上与当前最优可解释方法相当，同时实现了最低的认知复杂度。代码可在https://github.com/pyt19/ProtoSolo获取。
英文摘要：
Although interpretable prototype networks have improved the transparency of deep learning image classification, the need for multiple prototypes in collaborative decision-making increases cognitive complexity and hinders user understanding. To solve this problem, this paper proposes a novel interpretable deep architecture for image classification, called ProtoSolo. Unlike existing prototypical networks, ProtoSolo requires activation of only a single prototype to complete the classification. This design significantly simplifies interpretation, as the explanation for each class requires displaying only the prototype with the highest similarity score and its corresponding feature map. Additionally, the traditional full-channel feature vector is replaced with a feature map for similarity comparison and prototype learning, enabling the use of richer global information within a single-prototype activation decision. A non-projection prototype learning strategy is also introduced to preserve the association between the prototype and image patch while avoiding abrupt structural changes in the network caused by projection, which can affect classification performance. Experiments on the CUB-200-2011 and Stanford Cars datasets demonstrate that ProtoSolo matches state-of-the-art interpretable methods in classification accuracy while achieving the lowest cognitive complexity. The code is available at https://github.com/pyt19/ProtoSolo.
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。
