Probenet: Probing Deep Networks

Jae Hyeok Lee; Seong Tae Kim; Yong Man Ro

doi:10.1109/ICIP.2019.8803428

Probenet: Probing Deep Networks

Jae Hyeok Lee
, Seong Tae Kim
, Yong Man Ro

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

Despite the rapid progress of deep learning research in recent years, interpreting deep network is still quite challenging. Interpreting deep networks is essential to both end-users and developers since it gives confidence in the usage of the deep network. This paper deals with a method for interpreting deep networks, especially visual interpretation. In order to get visual interpretation from a target deep network, we propose a ProbeNet that provides a decomposed visual interpretation of the target deep network. The ProbeNet decomposes the feature representations of the point of the target deep network into human interpretable units. Furthermore, the ProbeNet provides kernel-level analysis about the target deep network. In experiments, visual interpretation of two different target deep networks showed the usefulness of the ProbeNet to interpret target deep networks.

Original language	English
Title of host publication	2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
Publisher	IEEE Computer Society
Pages	3821-3825
Number of pages	5
ISBN (Electronic)	9781538662496
DOIs	https://doi.org/10.1109/ICIP.2019.8803428
Publication status	Published - Sept 2019
Event	26th IEEE International Conference on Image Processing, ICIP 2019 - Taipei, Taiwan, Province of China Duration: 22 Sept 2019 → 25 Sept 2019

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2019-September
ISSN (Print)	1522-4880

Conference

Conference	26th IEEE International Conference on Image Processing, ICIP 2019
Country/Territory	Taiwan, Province of China
City	Taipei
Period	22/09/19 → 25/09/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

Deep network interpretation
Deep network probing
Human-understandable
ProbeNet

Access to Document

10.1109/ICIP.2019.8803428

Cite this

@inproceedings{9ef3b804d7cd4a8b8ab8d33927f4cfcf,

title = "Probenet: Probing Deep Networks",

abstract = "Despite the rapid progress of deep learning research in recent years, interpreting deep network is still quite challenging. Interpreting deep networks is essential to both end-users and developers since it gives confidence in the usage of the deep network. This paper deals with a method for interpreting deep networks, especially visual interpretation. In order to get visual interpretation from a target deep network, we propose a ProbeNet that provides a decomposed visual interpretation of the target deep network. The ProbeNet decomposes the feature representations of the point of the target deep network into human interpretable units. Furthermore, the ProbeNet provides kernel-level analysis about the target deep network. In experiments, visual interpretation of two different target deep networks showed the usefulness of the ProbeNet to interpret target deep networks.",

keywords = "Deep network interpretation, Deep network probing, Human-understandable, ProbeNet",

author = "Lee, \{Jae Hyeok\} and Kim, \{Seong Tae\} and Ro, \{Yong Man\}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 26th IEEE International Conference on Image Processing, ICIP 2019 ; Conference date: 22-09-2019 Through 25-09-2019",

year = "2019",

month = sep,

doi = "10.1109/ICIP.2019.8803428",

language = "English",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "3821--3825",

booktitle = "2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings",

address = "United States",

}

Lee, JH, Kim, ST & Ro, YM 2019, Probenet: Probing Deep Networks. in 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings., 8803428, Proceedings - International Conference on Image Processing, ICIP, vol. 2019-September, IEEE Computer Society, pp. 3821-3825, 26th IEEE International Conference on Image Processing, ICIP 2019, Taipei, Taiwan, Province of China, 22/09/19. https://doi.org/10.1109/ICIP.2019.8803428

Probenet: Probing Deep Networks. / Lee, Jae Hyeok; Kim, Seong Tae; Ro, Yong Man.
2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings. IEEE Computer Society, 2019. p. 3821-3825 8803428 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2019-September).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Probenet

T2 - 26th IEEE International Conference on Image Processing, ICIP 2019

AU - Lee, Jae Hyeok

AU - Kim, Seong Tae

AU - Ro, Yong Man

PY - 2019/9

Y1 - 2019/9

N2 - Despite the rapid progress of deep learning research in recent years, interpreting deep network is still quite challenging. Interpreting deep networks is essential to both end-users and developers since it gives confidence in the usage of the deep network. This paper deals with a method for interpreting deep networks, especially visual interpretation. In order to get visual interpretation from a target deep network, we propose a ProbeNet that provides a decomposed visual interpretation of the target deep network. The ProbeNet decomposes the feature representations of the point of the target deep network into human interpretable units. Furthermore, the ProbeNet provides kernel-level analysis about the target deep network. In experiments, visual interpretation of two different target deep networks showed the usefulness of the ProbeNet to interpret target deep networks.

AB - Despite the rapid progress of deep learning research in recent years, interpreting deep network is still quite challenging. Interpreting deep networks is essential to both end-users and developers since it gives confidence in the usage of the deep network. This paper deals with a method for interpreting deep networks, especially visual interpretation. In order to get visual interpretation from a target deep network, we propose a ProbeNet that provides a decomposed visual interpretation of the target deep network. The ProbeNet decomposes the feature representations of the point of the target deep network into human interpretable units. Furthermore, the ProbeNet provides kernel-level analysis about the target deep network. In experiments, visual interpretation of two different target deep networks showed the usefulness of the ProbeNet to interpret target deep networks.

KW - Deep network interpretation

KW - Deep network probing

KW - Human-understandable

KW - ProbeNet

UR - https://www.scopus.com/pages/publications/85076803101

U2 - 10.1109/ICIP.2019.8803428

DO - 10.1109/ICIP.2019.8803428

M3 - Conference contribution

AN - SCOPUS:85076803101

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 3821

EP - 3825

BT - 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings

PB - IEEE Computer Society

Y2 - 22 September 2019 through 25 September 2019

ER -

Probenet: Probing Deep Networks

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this