Gemi Tanima için Derin Mesafe Metrik Öǧrenmesi

Translated title of the contribution: Deep distance metric learning for maritime vessel identification

Erhan Gundogdu, Berkan Solmaz, Aykut Koc, Veysel Yucesoy, A. Aydin Alatan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper addresses the problem of maritime vessel identification by exploiting the state-of-the-art techniques of distance metric learning and deep convolutional neural networks since vessels are the key constituents of marine surveillance. In order to increase the performance of visual vessel identification, we propose a joint learning framework which considers a classification and a distance metric learning cost function. The proposed method utilizes the quadruplet samples from a diverse image dataset to learn the ranking of the distances for hierarchical levels of labeling. The proposed method performs favorably well for vessel identification task against the conventional use of neuron activations towards the final layers of the classification networks. The proposed method achieves 60 percent vessel identification accuracy for 3965 different vessels without sacrificing vessel type classification accuracy.

Original languageTurkish
Title of host publication2017 25th Signal Processing and Communications Applications Conference, SIU 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509064946
DOIs
StatePublished - Jun 27 2017
Externally publishedYes
Event25th Signal Processing and Communications Applications Conference, SIU 2017 - Antalya, Turkey
Duration: May 15 2017May 18 2017

Publication series

Name2017 25th Signal Processing and Communications Applications Conference, SIU 2017

Conference

Conference
CountryTurkey
CityAntalya
Period5/15/175/18/17

Fingerprint

Cost functions
Labeling
Neurons
Chemical activation
Neural networks

Keywords

  • deep learning
  • distance metric learning
  • vessel identification

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing

Cite this

Gundogdu, E., Solmaz, B., Koc, A., Yucesoy, V., & Alatan, A. A. (2017). Gemi Tanima için Derin Mesafe Metrik Öǧrenmesi. In 2017 25th Signal Processing and Communications Applications Conference, SIU 2017 [7960170] (2017 25th Signal Processing and Communications Applications Conference, SIU 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SIU.2017.7960170

Gemi Tanima için Derin Mesafe Metrik Öǧrenmesi. / Gundogdu, Erhan; Solmaz, Berkan; Koc, Aykut; Yucesoy, Veysel; Alatan, A. Aydin.

2017 25th Signal Processing and Communications Applications Conference, SIU 2017. Institute of Electrical and Electronics Engineers Inc., 2017. 7960170 (2017 25th Signal Processing and Communications Applications Conference, SIU 2017).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Gundogdu, E, Solmaz, B, Koc, A, Yucesoy, V & Alatan, AA 2017, Gemi Tanima için Derin Mesafe Metrik Öǧrenmesi. in 2017 25th Signal Processing and Communications Applications Conference, SIU 2017., 7960170, 2017 25th Signal Processing and Communications Applications Conference, SIU 2017, Institute of Electrical and Electronics Engineers Inc., 25th Signal Processing and Communications Applications Conference, SIU 2017, Antalya, Turkey, 5/15/17. https://doi.org/10.1109/SIU.2017.7960170
Gundogdu E, Solmaz B, Koc A, Yucesoy V, Alatan AA. Gemi Tanima için Derin Mesafe Metrik Öǧrenmesi. In 2017 25th Signal Processing and Communications Applications Conference, SIU 2017. Institute of Electrical and Electronics Engineers Inc. 2017. 7960170. (2017 25th Signal Processing and Communications Applications Conference, SIU 2017). https://doi.org/10.1109/SIU.2017.7960170
Gundogdu, Erhan ; Solmaz, Berkan ; Koc, Aykut ; Yucesoy, Veysel ; Alatan, A. Aydin. / Gemi Tanima için Derin Mesafe Metrik Öǧrenmesi. 2017 25th Signal Processing and Communications Applications Conference, SIU 2017. Institute of Electrical and Electronics Engineers Inc., 2017. (2017 25th Signal Processing and Communications Applications Conference, SIU 2017).
@inproceedings{9f65739b16f94cbeab98fdfda90a26ee,
title = "Gemi Tanima i{\cc}in Derin Mesafe Metrik {\"O}ǧrenmesi",
abstract = "This paper addresses the problem of maritime vessel identification by exploiting the state-of-the-art techniques of distance metric learning and deep convolutional neural networks since vessels are the key constituents of marine surveillance. In order to increase the performance of visual vessel identification, we propose a joint learning framework which considers a classification and a distance metric learning cost function. The proposed method utilizes the quadruplet samples from a diverse image dataset to learn the ranking of the distances for hierarchical levels of labeling. The proposed method performs favorably well for vessel identification task against the conventional use of neuron activations towards the final layers of the classification networks. The proposed method achieves 60 percent vessel identification accuracy for 3965 different vessels without sacrificing vessel type classification accuracy.",
keywords = "deep learning, distance metric learning, vessel identification",
author = "Erhan Gundogdu and Berkan Solmaz and Aykut Koc and Veysel Yucesoy and Alatan, {A. Aydin}",
year = "2017",
month = "6",
day = "27",
doi = "10.1109/SIU.2017.7960170",
language = "Turkish",
series = "2017 25th Signal Processing and Communications Applications Conference, SIU 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2017 25th Signal Processing and Communications Applications Conference, SIU 2017",

}

TY - GEN

T1 - Gemi Tanima için Derin Mesafe Metrik Öǧrenmesi

AU - Gundogdu, Erhan

AU - Solmaz, Berkan

AU - Koc, Aykut

AU - Yucesoy, Veysel

AU - Alatan, A. Aydin

PY - 2017/6/27

Y1 - 2017/6/27

N2 - This paper addresses the problem of maritime vessel identification by exploiting the state-of-the-art techniques of distance metric learning and deep convolutional neural networks since vessels are the key constituents of marine surveillance. In order to increase the performance of visual vessel identification, we propose a joint learning framework which considers a classification and a distance metric learning cost function. The proposed method utilizes the quadruplet samples from a diverse image dataset to learn the ranking of the distances for hierarchical levels of labeling. The proposed method performs favorably well for vessel identification task against the conventional use of neuron activations towards the final layers of the classification networks. The proposed method achieves 60 percent vessel identification accuracy for 3965 different vessels without sacrificing vessel type classification accuracy.

AB - This paper addresses the problem of maritime vessel identification by exploiting the state-of-the-art techniques of distance metric learning and deep convolutional neural networks since vessels are the key constituents of marine surveillance. In order to increase the performance of visual vessel identification, we propose a joint learning framework which considers a classification and a distance metric learning cost function. The proposed method utilizes the quadruplet samples from a diverse image dataset to learn the ranking of the distances for hierarchical levels of labeling. The proposed method performs favorably well for vessel identification task against the conventional use of neuron activations towards the final layers of the classification networks. The proposed method achieves 60 percent vessel identification accuracy for 3965 different vessels without sacrificing vessel type classification accuracy.

KW - deep learning

KW - distance metric learning

KW - vessel identification

UR - http://www.scopus.com/inward/record.url?scp=85026293455&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85026293455&partnerID=8YFLogxK

U2 - 10.1109/SIU.2017.7960170

DO - 10.1109/SIU.2017.7960170

M3 - Conference contribution

AN - SCOPUS:85026293455

T3 - 2017 25th Signal Processing and Communications Applications Conference, SIU 2017

BT - 2017 25th Signal Processing and Communications Applications Conference, SIU 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -