TY - GEN
T1 - Learning discriminative correlation subspace for heterogeneous domain adaptation
AU - Yan, Yuguang
AU - Li, Wen
AU - NG, Kwok Po
AU - Tan, Mingkui
AU - Wu, Hanrui
AU - Min, Huaqing
AU - Wu, Qingyao
N1 - Funding Information:
This work is supported by the Guangzhou Key Laboratory of Robotics and Intelligent Software (15180007), NSFC (61502177 and 61602185), HKBU (12306616 and 12302715).
PY - 2017/8
Y1 - 2017/8
N2 - Domain adaptation aims to reduce the effort on collecting and annotating target data by leveraging knowledge from a different source domain. The domain adaptation problem will become extremely challenging when the feature spaces of the source and target domains are different, which is also known as the heterogeneous domain adaptation (HDA) problem. In this paper, we propose a novel HDA method to find the optimal discriminative correlation subspace for the source and target data. The discriminative correlation subspace is inherited from the canonical correlation subspace between the source and target data, and is further optimized to maximize the discriminative ability for the target domain classifier. We formulate a joint objective in order to simultaneously learn the discriminative correlation subspace and the target domain classifier. We then apply an alternating direction method of multiplier (ADMM) algorithm to address the resulting non-convex optimization problem. Comprehensive experiments on two real-world data sets demonstrate the effectiveness of the proposed method compared to the state-of-the-art methods.
AB - Domain adaptation aims to reduce the effort on collecting and annotating target data by leveraging knowledge from a different source domain. The domain adaptation problem will become extremely challenging when the feature spaces of the source and target domains are different, which is also known as the heterogeneous domain adaptation (HDA) problem. In this paper, we propose a novel HDA method to find the optimal discriminative correlation subspace for the source and target data. The discriminative correlation subspace is inherited from the canonical correlation subspace between the source and target data, and is further optimized to maximize the discriminative ability for the target domain classifier. We formulate a joint objective in order to simultaneously learn the discriminative correlation subspace and the target domain classifier. We then apply an alternating direction method of multiplier (ADMM) algorithm to address the resulting non-convex optimization problem. Comprehensive experiments on two real-world data sets demonstrate the effectiveness of the proposed method compared to the state-of-the-art methods.
UR - http://www.scopus.com/inward/record.url?scp=85031892773&partnerID=8YFLogxK
UR - https://www.ijcai.org/proceedings/2017/
U2 - 10.24963/ijcai.2017/454
DO - 10.24963/ijcai.2017/454
M3 - Conference contribution
AN - SCOPUS:85031892773
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 3252
EP - 3258
BT - Proceedings of the 26th International Joint Conference on Artificial Intelligence, IJCAI 2017
A2 - Sierra, Carles
PB - International Joint Conferences on Artificial Intelligence
T2 - 26th International Joint Conference on Artificial Intelligence, IJCAI 2017
Y2 - 19 August 2017 through 25 August 2017
ER -