no code implementations • 11 Mar 2024 • Angeliki Dimitriou, Maria Lymperaiou, Giorgos Filandrianos, Konstantinos Thomas, Giorgos Stamou
With a focus on the visual domain, we represent images as scene graphs and obtain their GNN embeddings to bypass solving the NP-hard graph similarity problem for all input pairs, an integral part of the CE computation process.
1 code implementation • 28 May 2023 • Edmund Dervakos, Konstantinos Thomas, Giorgos Filandrianos, Giorgos Stamou
In this work, we build on these ideas, and propose a framework that provides counterfactual explanations in terms of knowledge graphs.
1 code implementation • 4 Mar 2023 • Maria Lymperaiou, Konstantinos Thomas, Giorgos Stamou
Image classification has been one of the most popular tasks in Deep Learning, seeing an abundance of impressive implementations each year.
no code implementations • 2 Mar 2023 • Maria Lymperaiou, Giorgos Filandrianos, Konstantinos Thomas, Giorgos Stamou
Evaluation of generative models has been an underrepresented field despite the surge of generative architectures.
1 code implementation • AAAI-MAKE 2022 • Giorgos Filandrianos, Konstantinos Thomas, Edmund Dervakos1, Giorgos Stamou1
We propose a framework for generating counterfactual explanations of black-box classifiers, which answer the question “What has to change for this to be classified as X instead of Y?” in terms of given domain knowledge.
no code implementations • AAAI-MAKE 2021 • Edmund Dervakos, Giorgos Filandrianos, Konstantinos Thomas, Alexios Mandalios, Chrysoula Zerva, Giorgos Stamou
The rapid growth of scientific literature in the biomedical and clinical domain has significantly com- plicated the identification of information of interest by researchers as well as other practitioners.
Ranked #1 on Information Retrieval on Ohsumed