Search Results for author: Galip Ümit Yolcu

Found 2 papers, 1 papers with code

DualView: Data Attribution from the Dual Perspective

2 code implementations19 Feb 2024 Galip Ümit Yolcu, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin

In this work we present DualView, a novel method for post-hoc data attribution based on surrogate modelling, demonstrating both high computational efficiency, as well as good evaluation results.

Computational Efficiency

Optimizing Explanations by Network Canonization and Hyperparameter Search

no code implementations30 Nov 2022 Frederik Pahde, Galip Ümit Yolcu, Alexander Binder, Wojciech Samek, Sebastian Lapuschkin

We further suggest a XAI evaluation framework with which we quantify and compare the effect sof model canonization for various XAI methods in image classification tasks on the Pascal-VOC and ILSVRC2017 datasets, as well as for Visual Question Answering using CLEVR-XAI.

Explainable Artificial Intelligence (XAI) Image Classification +2

Cannot find the paper you are looking for? You can Submit a new open access paper.