TY - GEN
T1 - Coupled support vector machines for supervised domain adaptation
AU - Demakethepalli Venkateswara, Hemanth
AU - Lade, Prasanth
AU - Ye, Jieping
AU - Panchanathan, Sethuraman
N1 - Funding Information:
National Science Foundation (NSF)
Publisher Copyright:
© 2015 ACM.
PY - 2015/10/13
Y1 - 2015/10/13
N2 - Popular domain adaptation (DA) techniques learn a classifier for the target domain by sampling relevant data points from the source and combining it with the target data. We present a Support Vector Machine (SVM) based supervised DA technique, where the similarity between source and target domains is mod-eled as the similarity between their SVM decision boundaries. We couple the source and target SVMs and reduce the model to a standard single SVM. We test the Coupled-SVM on multiple datasets and compare our results with other popular SVM based DA approaches.
AB - Popular domain adaptation (DA) techniques learn a classifier for the target domain by sampling relevant data points from the source and combining it with the target data. We present a Support Vector Machine (SVM) based supervised DA technique, where the similarity between source and target domains is mod-eled as the similarity between their SVM decision boundaries. We couple the source and target SVMs and reduce the model to a standard single SVM. We test the Coupled-SVM on multiple datasets and compare our results with other popular SVM based DA approaches.
KW - Coupled SVM
KW - Supervised Domain Adaptation
UR - http://www.scopus.com/inward/record.url?scp=84962784482&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84962784482&partnerID=8YFLogxK
U2 - 10.1145/2733373.2806334
DO - 10.1145/2733373.2806334
M3 - Conference contribution
AN - SCOPUS:84962784482
T3 - MM 2015 - Proceedings of the 2015 ACM Multimedia Conference
SP - 1295
EP - 1298
BT - MM 2015 - Proceedings of the 2015 ACM Multimedia Conference
PB - Association for Computing Machinery, Inc
T2 - 23rd ACM International Conference on Multimedia, MM 2015
Y2 - 26 October 2015 through 30 October 2015
ER -