Sight-seeing in the eyes of deep neural networks

Conference paper (2018)

Authors

S. Khademi Pattern Recognition and Bioinformatics -

X. Shi Pattern Recognition and Bioinformatics -

Tino Mager History, Form & Aesthetics - Architecture and the Built Environment

R.M. Siebes Pattern Recognition and Bioinformatics - , Vrije Universiteit Amsterdam

C.M. Hein History, Form & Aesthetics - Architecture and the Built Environment

Victor de Boer Vrije Universiteit Amsterdam

J.C. van Gemert Pattern Recognition and Bioinformatics -

Research Group

Pattern Recognition and Bioinformatics () (TU Delft)

DOI: https://doi.org/10.1109/eScience.2018.00125

Interpretability Classification Visualization Convolutional neural network (CNN) Place recognition

To reference this document use:

http://resolver.tudelft.nl/uuid:c7b3733a-9848-4e55-996f-978b49c98a60

More Info

expand_more

Published Date

2018

Language

English

Reuse Rights

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.

Faculty

Electrical Engineering, Mathematics and Computer Science

Department

Intelligent Systems

Research Group

Pattern Recognition and Bioinformatics

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.

Files

08588744.pdf

(pdf | 0.836 Mb)

- Embargo expired in 01-06-2019