Toward Scalable and Unified Example-based Explanation and Outlier Detection

Abstract

When neural networks are employed for high-stakes decision-making, it is desirable that they provide explanations for their prediction in order for us to understand the features that have contributed to the decision. At the same time, it is important to flag potential outliers for in-depth verification by domain experts. In this work we propose to unify two differing aspects of explainability with outlier detection. We argue for a broader adoption of prototype-based student networks capable of providing an example-based explanation for their prediction and at the same time identify regions of similarity between the predicted sample and the examples. The examples are real prototypical cases sampled from the training set via our novel iterative prototype replacement algorithm. Furthermore, we propose to use the prototype similarity scores for identifying outliers. We compare performances in terms of the classification, explanation quality, and outlier detection of our proposed network with other baselines. We show that our prototype-based networks beyond similarity kernels deliver meaningful explanations and promising outlier detection results without compromising classification accuracy.

Accepted in IEEE Transactions on Image Processing

References in corpus (6)

• Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
• Deep Anomaly Detection with Outlier Exposure
• Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions
• Building and Interpreting Deep Similarity Models
• Statistical Analysis of Nearest Neighbor Methods for Anomaly Detection
• Interpretable Image Recognition with Hierarchical Prototypes