TY - GEN
T1 - Task-driven dictionary learning based on convolutional neural network features
AU - Tirer, Tom
AU - Giryes, Raja
N1 - Publisher Copyright:
© EURASIP 2018.
PY - 2018/11/29
Y1 - 2018/11/29
N2 - Modeling data as a linear combination of a few elements from a learned dictionary has been used extensively in the recent decade in many fields, such as machine learning and signal processing. The learning of the dictionary is usually performed in an unsupervised manner, which is most suitable for regression tasks. However, for other purposes, e.g. image classification, it is advantageous to learn a dictionary from the data in a supervised way. Such an approach has been referred to as task-driven dictionary learning. In this work, we integrate this approach with deep learning. We modify this strategy such that the dictionary is learned for features obtained by a convolutional neural network (CNN). The parameters of the CNN are learned simultaneously with the task-driven dictionary and with the classifier parameters.
AB - Modeling data as a linear combination of a few elements from a learned dictionary has been used extensively in the recent decade in many fields, such as machine learning and signal processing. The learning of the dictionary is usually performed in an unsupervised manner, which is most suitable for regression tasks. However, for other purposes, e.g. image classification, it is advantageous to learn a dictionary from the data in a supervised way. Such an approach has been referred to as task-driven dictionary learning. In this work, we integrate this approach with deep learning. We modify this strategy such that the dictionary is learned for features obtained by a convolutional neural network (CNN). The parameters of the CNN are learned simultaneously with the task-driven dictionary and with the classifier parameters.
UR - http://www.scopus.com/inward/record.url?scp=85059804045&partnerID=8YFLogxK
U2 - 10.23919/EUSIPCO.2018.8553495
DO - 10.23919/EUSIPCO.2018.8553495
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85059804045
T3 - European Signal Processing Conference
SP - 1885
EP - 1889
BT - 2018 26th European Signal Processing Conference, EUSIPCO 2018
PB - European Signal Processing Conference, EUSIPCO
T2 - 26th European Signal Processing Conference, EUSIPCO 2018
Y2 - 3 September 2018 through 7 September 2018
ER -