Robust Deep Interpretable Features for Binary Image Classification
Proceedings of the Northern Lights Deep Learning Workshop · 2021
DOI: 10.7557/18.5708 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the Northern Lights Deep Learning Workshop, 2021. Verfasst von Robert Hu und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The problem of interpretability for binary image classification is considered through the lens of kernel two-sample tests and generative modeling. A feature extraction framework coined Deep Interpretable Features (DIF) is developed, which is used in combination with IntroVAE, a generative model capable of high-resolution image synthesis. Experimental results on a variety of datasets, including COVID-19 chest x-rays demonstrate the benefits of combining deep generative models with the ideas from kernel-based hypothesis testing in moving towards more robust interpretable deep generative models.
Zitieren
APA
Hu, R., & Sejdinovic, D. (2021). Robust Deep Interpretable Features for Binary Image Classification. Proceedings of the Northern Lights Deep Learning Workshop. https://doi.org/10.7557/18.5708
Vancouver
Hu R, Sejdinovic D. Robust Deep Interpretable Features for Binary Image Classification. Proceedings of the Northern Lights Deep Learning Workshop. 2021. doi:10.7557/18.5708
BibTeX
@article{Hu2021,
author = {Hu, Robert and Sejdinovic, Dino},
title = {Robust Deep Interpretable Features for Binary Image Classification},
journal = {Proceedings of the Northern Lights Deep Learning Workshop},
year = {2021},
doi = {10.7557/18.5708}
}
EUVIMED