Supporting Safety Analysis of Image-processing DNNs through Clustering-based Approaches

TL;DR

This paper evaluates 99 clustering-based pipelines to improve safety analysis of image-processing DNNs, identifying effective methods for root cause analysis and failure scenario detection in safety-critical applications.

Contribution

It empirically compares diverse pipelines for DNN failure analysis, identifying the most effective combination of transfer learning, DBSCAN, and UMAP for clustering failures.

Findings

Best pipeline uses transfer learning, DBSCAN, and UMAP.

Clusters accurately group images by failure scenario.

Effective even for rare failure cases.

Abstract

The adoption of deep neural networks (DNNs) in safety-critical contexts is often prevented by the lack of effective means to explain their results, especially when they are erroneous. In our previous work, we proposed a white-box approach (HUDD) and a black-box approach (SAFE) to automatically characterize DNN failures. They both identify clusters of similar images from a potentially large set of images leading to DNN failures. However, the analysis pipelines for HUDD and SAFE were instantiated in specific ways according to common practices, deferring the analysis of other pipelines to future work. In this paper, we report on an empirical evaluation of 99 different pipelines for root cause analysis of DNN failures. They combine transfer learning, autoencoders, heatmaps of neuron relevance, dimensionality reduction techniques, and different clustering algorithms. Our results show that the best pipeline combines transfer learning, DBSCAN, and UMAP. It leads to clusters almost exclusively capturing images of the same failure scenario, thus facilitating root cause analysis. Further, it generates distinct clusters for each root cause of failure, thus enabling engineers to detect all the unsafe scenarios. Interestingly, these results hold even for failure scenarios that are only observed in a small percentage of the failing images.