This repository contains the source code and the data of the paper "DeepMetis: Augmenting a Deep Learning Test Set to Increase its Mutation Score" by V. Riccio, N. Humbatova, G. Jahangirova, and P. Tonella, to be published in the Proceedings of the 36th IEEE/ACM International Conference on Automated Software Engineering (ASE 2021).
The package is structured as follows:
- DeepMetis-MNIST contains the DeepMetis tool adapted to the handwritten digit classification case study and the instructions on how to use it. It also contains the raw experimental data and the scripts to obtain the results reported in the paper for the MNIST case study;
- DeepMetis-UE contains the DeepMetis tool adapted to the eye gaze prediction case study and the instructions on how to use it. It also contains the raw experimental data and the scripts to obtain the results reported in the paper for the UnityEyes case study;
- installation guide contains a quick installation guide of the tool.
- preprint is the preprint version of our paper describing DeepMetis.
Note: each sub-package contains further specific instructions.
The software we developed is distributed under MIT license. See the license file.
For any related question, please contact its authors:
- Vincenzo Riccio (vincenzo.riccio@usi.ch)
- Nargiz Humbatova (nargiz.humbatova@usi.ch)
- Gunel Jahangirova (gunel.jahangirova@usi.ch)
- Paolo Tonella (paolo.tonella@usi.ch).
If our work helps your research, please cite DeepMetis in your publications. Here is an example BibTeX entry:
@inproceedings{DeepMetis_ASE_2021,
title= {DeepMetis: Augmenting a Deep Learning Test Set to Increase its Mutation Score},
author= {Vincenzo Riccio and Nargiz Humbatova and Gunel Jahangirova and Paolo Tonella},
booktitle= {Proceedings of the 36th IEEE/ACM International Conference on Automated Software Engineering},
series= {ASE '21},
publisher= {IEEE/ACM},
year= {2021}
}