Visualizing Classification Structure of Large-Scale Classifiers
This work addresses the need for interpretability and analysis of classification behavior in large-scale systems, though it appears incremental as it builds on existing visualization techniques.
The authors tackled the problem of understanding class relationships in large-scale classifiers by proposing a new measure to compute class similarity from prediction scores, and they demonstrated that visualizing this similarity matrix can reveal hierarchical structures and relationships among classes.
We propose a measure to compute class similarity in large-scale classification based on prediction scores. Such measure has not been formally pro-posed in the literature. We show how visualizing the class similarity matrix can reveal hierarchical structures and relationships that govern the classes. Through examples with various classifiers, we demonstrate how such structures can help in analyzing the classification behavior and in inferring potential corner cases. The source code for one example is available as a notebook at https://github.com/bilalsal/blocks