Global interpretability is a vital requirement for image classification applications. Existing interpretability methods mainly explain a model behavior by identifying salient image patches, which require manual efforts from users to make sense of, and also do not typically support model validation with questions that investigate multiple visual concepts.

In this paper, we introduce a scalable human-in-the-loop approach for global interpretability. Salient image areas identified by local interpretability methods are annotated with semantic concepts, which are then aggregated into a structured representation of images to facilitate automatic statistical analysis of model behavior. We show that this approach can answer interpretability needs for both model validation and exploration, and provides semantically more diverse, informative, and relevant explanations while still allowing for scalable and cost-efficient execution.

Code: link, https://github.com/psoilis/SECA

Data: available upon request due to the large size of the files