Write a Blog >>
ICSE 2022
Sun 8 - Fri 27 May 2022
Fri 13 May 2022 03:00 - 03:15 at ICSE Demo room 1 - Machine Learning with and for SE Chair(s): Xiaoyuan Xie

We present HUDD, a tool that supports safety analysis practices for systems integrating Deep Neural Networks (DNNs) by automatically identifying the root causes for DNN errors and retraining the DNN. Its name stands for Heatmap-based Unsupervised Debugging of DNNs, it automatically clusters together error-inducing images whose results are due to common subsets of DNN neurons. The generated clusters 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

Fri 13 May

Displayed time zone: Eastern Time (US & Canada) change

03:00 - 04:00
Machine Learning with and for SEDEMO - Demonstrations at ICSE Demo room 1
Chair(s): Xiaoyuan Xie School of Computer Science, Wuhan University, China
03:00
15m
Demonstration
HUDD: A tool to debug DNNs for safety analysis
DEMO - Demonstrations
Hazem FAHMY University of Luxembourg, Fabrizio Pastore University of Luxembourg, Lionel Briand University of Luxembourg; University of Ottawa
Pre-print Media Attached
03:15
15m
Demonstration
WhyGen: Explaining ML-powered Code Generation by Referring to Training Examples
DEMO - Demonstrations
Weixiang Yan Beijing University of Posts and Telecommunications, Yuanchun Li Microsoft Research
DOI Pre-print Media Attached
03:30
15m
Demonstration
SEbox4DL: A Modular Software Engineering Toolbox for Deep Learning Models
DEMO - Demonstrations
Zhengyuan Wei City University of Hong Kong, Hong Kong, Haipeng Wang City University of Hong Kong, Zhen Yang City University of Hong Kong, China, Wing-Kwong Chan City University of Hong Kong, Hong Kong
Hide past events

Information for Participants
Fri 13 May 2022 03:00 - 04:00 at ICSE Demo room 1 - Machine Learning with and for SE Chair(s): Xiaoyuan Xie
Info for room ICSE Demo room 1:

Click here to go to the room on Midspace