ProtoSolo: Interpretable Image Classification via Single-Prototype Activation
This addresses the need for simpler interpretability in deep learning image classification for users, though it is incremental as it builds on existing prototype networks.
The paper tackled the problem of high cognitive complexity in interpretable prototype networks for image classification by proposing ProtoSolo, which uses only a single prototype activation, and it matched state-of-the-art accuracy on CUB-200-2011 and Stanford Cars datasets while achieving the lowest cognitive complexity.
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.