Supporting DNN Safety Analysis and Retraining through Heatmap-based Unsupervised Learning

This repository provides the data used for the experiments of the paper  "Supporting DNN Safety Analysis and Retraining through Heatmap-based Unsupervised Learning" by Hazem Fahmy, Fabrizio Pastore, Mojtaba Bagherzadeh, and Lionel Briand appearing in IEEE Transactions on Reliability (doi: 10.1109/TR.2021.3074750)

Deep neural networks (DNNs) are increasingly important in safety-critical systems, for example in their perception layer to analyze images. Unfortunately, there is a lack of methods to ensure the functional safety of DNN-based components.

We observe three major challenges with existing practices regarding DNNs in safety-critical systems: (1) scenarios that are underrepresented in the test set may lead to serious safety violation risks, but may, however, remain unnoticed; (2) char- acterizing such high-risk scenarios is critical for safety analysis; (3) retraining DNNs to address these risks is poorly supported when causes of violations are difficult to determine.

To address these problems in the context of DNNs analyzing images, we propose HUDD, an approach that automatically supports the identification of root causes for DNN errors. HUDD identifies root causes by applying a clustering algorithm to heatmaps capturing the relevance of every DNN neuron on the DNN outcome. Also, HUDD retrains DNNs with images that are automatically selected based on their relatedness to the identified image clusters.

We evaluated HUDD with DNNs from the automotive domain. HUDD was able to identify all the distinct root causes of DNN errors, thus supporting safety analysis. Also, our retraining approach has shown to be more effective at improving DNN accuracy than existing approaches.