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
N1 - Publisher Copyright:
© 2017 IEEE.
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.
T2 - 25th Signal Processing and Communications Applications Conference, SIU 2017
Y2 - 15 May 2017 through 18 May 2017
ER -