Multiple-Boundary Clustering and Prioritization to Promote Neural Network Retraining
Abstract
With the increasing application of deep learning (DL) models in many safety-critical scenarios, effective and efficient DL testing techniques are much in demand to improve the quality of DL models. One of the major challenges is the data gap between the training data to construct the models and the testing data to evaluate them. To bridge the gap, testers aim to collect an effective subset of inputs from the testing contexts, with limited labeling effort, for retraining DL models.
BibTeX
@inproceedings{Shen-al:ASE20,
author = {Weijun Shen and
Yanhui Li and
Lin Chen and
Yuanlei Han and
Yuming Zhou and
Baowen Xu},
title = {{Multiple-Boundary} Clustering and Prioritization to Promote Neural Network Retraining},
booktitle = {ASE},
pages = {410--422},
publisher = {{IEEE}},
year = {2020},
}