HUDD: A tool to debug DNNs for safety analysis

Hazem Fahmy, Fabrizio Pastore, Lionel Briand

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We present HUDD, a tool that supports safety analysis practices for systems enabled by Deep Neural Networks (DNNs) by automatically identifying the root causes for DNN errors and retraining the DNN. HUDD stands for Heatmap-based Unsupervised Debugging of DNNs, it automatically clusters error-inducing images whose results are due to common subsets of DNN neurons. The intent is for the generated clusters to group error-inducing images having common characteristics, that is, having a common root cause.HUDD identifies root causes by applying a clustering algorithm to matrices (i.e., 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. Our empirical evaluation with DNNs from the automotive domain have shown that HUDD automatically identifies 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. A demo video of HUDD is available at https://youtu.be/drjVakP7jdU.

Original languageEnglish
Title of host publicationProceedings - 2022 ACM/IEEE 44th International Conference on Software Engineering
Subtitle of host publicationCompanion Proceedings, ICSE-Companion 2022
PublisherIEEE Computer Society
Pages100-104
Number of pages5
ISBN (Electronic)9781665495981
DOIs
Publication statusPublished - 2022
Externally publishedYes
Event44th ACM/IEEE International Conference on Software Engineering: Companion, ICSE-Companion 2022 - Pittsburgh, United States
Duration: 22 May 202227 May 2022

Publication series

NameProceedings - International Conference on Software Engineering
ISSN (Print)0270-5257

Conference

Conference44th ACM/IEEE International Conference on Software Engineering: Companion, ICSE-Companion 2022
Country/TerritoryUnited States
CityPittsburgh
Period22/05/2227/05/22

Keywords

  • DNN debugging
  • Functional Safety Analysis

Fingerprint

Dive into the research topics of 'HUDD: A tool to debug DNNs for safety analysis'. Together they form a unique fingerprint.

Cite this