Sight-Seeing in the Eyes of Deep Neural Networks

Seyran Khademi, Xiangwei Shi, Tino Mager, Ronald Siebes, Carola Hein, Victor De Boer, Jan Van Gemert

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

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.

LanguageEnglish
Title of host publicationProceedings - IEEE 14th International Conference on eScience, e-Science 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages407-408
Number of pages2
ISBN (Electronic)9781538691564
DOIs
Publication statusPublished - 24 Dec 2018
Event14th IEEE International Conference on eScience, e-Science 2018 - Amsterdam, Netherlands
Duration: 29 Oct 20181 Nov 2018

Conference

Conference14th IEEE International Conference on eScience, e-Science 2018
CountryNetherlands
CityAmsterdam
Period29/10/181/11/18

Fingerprint

Neural Networks
filter
Neural networks
Interpretability
Filter
Network Architecture
Network architecture
experiment
Classify
Deep neural networks
Experiment
Experiments
parameter

Keywords

  • Classification
  • Convolutional neural network (CNN)
  • Interpretability
  • Place recognition
  • Visualization

Cite this

Khademi, S., Shi, X., Mager, T., Siebes, R., Hein, C., De Boer, V., & Van Gemert, J. (2018). Sight-Seeing in the Eyes of Deep Neural Networks. In Proceedings - IEEE 14th International Conference on eScience, e-Science 2018 (pp. 407-408). [8588744] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/eScience.2018.00125
Khademi, Seyran ; Shi, Xiangwei ; Mager, Tino ; Siebes, Ronald ; Hein, Carola ; De Boer, Victor ; Van Gemert, Jan. / Sight-Seeing in the Eyes of Deep Neural Networks. Proceedings - IEEE 14th International Conference on eScience, e-Science 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 407-408
@inproceedings{798d057ec1ff4064b43876dde2533c5f,
title = "Sight-Seeing in the Eyes of Deep Neural Networks",
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.",
keywords = "Classification, Convolutional neural network (CNN), Interpretability, Place recognition, Visualization",
author = "Seyran Khademi and Xiangwei Shi and Tino Mager and Ronald Siebes and Carola Hein and {De Boer}, Victor and {Van Gemert}, Jan",
year = "2018",
month = "12",
day = "24",
doi = "10.1109/eScience.2018.00125",
language = "English",
pages = "407--408",
booktitle = "Proceedings - IEEE 14th International Conference on eScience, e-Science 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Khademi, S, Shi, X, Mager, T, Siebes, R, Hein, C, De Boer, V & Van Gemert, J 2018, Sight-Seeing in the Eyes of Deep Neural Networks. in Proceedings - IEEE 14th International Conference on eScience, e-Science 2018., 8588744, Institute of Electrical and Electronics Engineers Inc., pp. 407-408, 14th IEEE International Conference on eScience, e-Science 2018, Amsterdam, Netherlands, 29/10/18. https://doi.org/10.1109/eScience.2018.00125

Sight-Seeing in the Eyes of Deep Neural Networks. / Khademi, Seyran; Shi, Xiangwei; Mager, Tino; Siebes, Ronald; Hein, Carola; De Boer, Victor; Van Gemert, Jan.

Proceedings - IEEE 14th International Conference on eScience, e-Science 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 407-408 8588744.

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Sight-Seeing in the Eyes of Deep Neural Networks

AU - Khademi, Seyran

AU - Shi, Xiangwei

AU - Mager, Tino

AU - Siebes, Ronald

AU - Hein, Carola

AU - De Boer, Victor

AU - Van Gemert, Jan

PY - 2018/12/24

Y1 - 2018/12/24

N2 - 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.

AB - 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.

KW - Classification

KW - Convolutional neural network (CNN)

KW - Interpretability

KW - Place recognition

KW - Visualization

UR - http://www.scopus.com/inward/record.url?scp=85061364522&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061364522&partnerID=8YFLogxK

U2 - 10.1109/eScience.2018.00125

DO - 10.1109/eScience.2018.00125

M3 - Conference contribution

SP - 407

EP - 408

BT - Proceedings - IEEE 14th International Conference on eScience, e-Science 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Khademi S, Shi X, Mager T, Siebes R, Hein C, De Boer V et al. Sight-Seeing in the Eyes of Deep Neural Networks. In Proceedings - IEEE 14th International Conference on eScience, e-Science 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 407-408. 8588744 https://doi.org/10.1109/eScience.2018.00125