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

Abstract

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) characterizing 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.

References in corpus (7)

• Ward's Hierarchical Clustering Method: Clustering Criterion and Agglomerative Algorithm
• Striving for Simplicity: The All Convolutional Net
• Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
• Active Learning for Convolutional Neural Networks: A Core-Set Approach
• Guiding Deep Learning System Testing using Surprise Adequacy
• Exploring the Landscape of Spatial Robustness
• Boosting Operational DNN Testing Efficiency through Conditioning

Cited by in corpus (6)

• Black-Box Testing of Deep Neural Networks Through Test Case Diversity
• DeepGD: A Multi-Objective Black-Box Test Selection Approach for Deep Neural Networks
• Black-box Safety Analysis and Retraining of DNNs based on Feature Extraction and Clustering
• Simulator-based explanation and debugging of hazard-triggering events in DNN-based safety-critical systems
• TEASMA: A Practical Methodology for Test Adequacy Assessment of Deep Neural Networks
• HUDD: A tool to debug DNNs for safety analysis