TY - GEN
T1 - Evrişimsel sinir aǧlarinin Gabor süzgeçleri ile ilklendirilmesi
AU - Ozbulak, Gokhan
AU - Ekenel, Hazim Kemal
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/7/5
Y1 - 2018/7/5
N2 - In transfer learning, for a given classification task, the learning from source domain into target domain is achieved by training/transferring a pre-trained network with data from target domain. During this process, a pre-trained network is a pre-requisite for transferring the knowledge from source domain into the target domain. In this study, to eliminate the need for such a pre-trained model, Gabor filters are utilized. In the proposed method, a Convolutional Neural Network is constructed by initializing its first convolutional layer, which represents the low-level features, such as corners and edges, with Gabor filters that have similar low-level characteristics. Experimental results on MNIST, CIFAR-10, and CIFAR-100 datasets show that Gabor filters based initialization of the network has similar characteristics with model transfer and can be applied for transfer learning without using a pre-trained model.
AB - In transfer learning, for a given classification task, the learning from source domain into target domain is achieved by training/transferring a pre-trained network with data from target domain. During this process, a pre-trained network is a pre-requisite for transferring the knowledge from source domain into the target domain. In this study, to eliminate the need for such a pre-trained model, Gabor filters are utilized. In the proposed method, a Convolutional Neural Network is constructed by initializing its first convolutional layer, which represents the low-level features, such as corners and edges, with Gabor filters that have similar low-level characteristics. Experimental results on MNIST, CIFAR-10, and CIFAR-100 datasets show that Gabor filters based initialization of the network has similar characteristics with model transfer and can be applied for transfer learning without using a pre-trained model.
KW - Convolutional neural networks
KW - Gabor filter
KW - Transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85050807386&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85050807386&partnerID=8YFLogxK
U2 - 10.1109/SIU.2018.8404757
DO - 10.1109/SIU.2018.8404757
M3 - Conference contribution
AN - SCOPUS:85050807386
T3 - 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018
SP - 1
EP - 4
BT - 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018
Y2 - 2 May 2018 through 5 May 2018
ER -