Sight-seeing in the eyes of deep neural networks
S Khademi (TU Delft - Pattern Recognition and Bioinformatics)
Xiangwei Shi (TU Delft - Pattern Recognition and Bioinformatics)
Tino Mager (TU Delft - History, Form & Aesthetics)
Ronald Maria Siebes (Vrije Universiteit Amsterdam, TU Delft - Pattern Recognition and Bioinformatics)
Carola Hein (TU Delft - History, Form & Aesthetics)
Victor De Boer (Vrije Universiteit Amsterdam)
J.C. Gemert (TU Delft - Pattern Recognition and Bioinformatics)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
We address the interpretability of convolutional neural networks (CNNs) for predicting a geo-location from an image. In a pilot experiment we classify images of Pittsburgh vs Tokyo and visualize the learned CNN filters. We found that varying the CNN architecture leads to variating in the visualized filters. This calls for further investigation of the effective parameters on the interpretability of CNNs.