What is a Tabby? Interpretable Model Decisions by Learning Attribute-Based Classification Criteria

State-of-the-art classification models are usually considered as black boxes since their decision processes are implicit to humans. On the contrary, human experts classify objects according to a set of explicit hierarchical criteria. For example, tabby is a domestic cat with stripes, dots, or lines, where tabby is defined by combining its superordinate category (domestic cat) and some certain attributes (e.g., has stripes). Inspired by this mechanism, we propose an interpretable Hierarchical Criteria Network (HCN) by additionally learning such criteria. To achieve this goal, images and semantic entities (e.g., taxonomies and attributes) are embedded into a common space, where each category can be represented by the linear combination of its superordinate category and a set of learned discriminative attributes. Specifically, a two-stream convolutional neural network (CNN) is elaborately devised, which embeds images and taxonomies with the two streams respectively. The model is trained by minimizing the prediction error of hierarchy labels on both streams. Extensive experiments on two widely studied datasets (CIFAR-100 and ILSVRC) demonstrate that HCN can learn meaningful attributes as well as reasonable and interpretable classification criteria. Therefore, the proposed method enables further human feedback for model correction as an additional benefit.

Automated summary

The proposed interpretable Hierarchical Criteria Network (HCN) aims to make classification models more understandable by learning explicit hierarchical criteria. The results show that HCN can learn meaningful attributes and reasonable interpretable classification criteria, providing further human feedback for model correction.