Transfer Joint Matching for Unsupervised Domain Adaptation

• Published in: 2014 IEEE Conference on Computer Vision and Pattern Recognition pp. 1410 - 1417
• Main Authors: Mingsheng Long, Jianmin Wang, Guiguang Ding, Jiaguang Sun, Yu, Philip S.
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.06.2014
• Subjects: Adaptation; Computer vision; Conferences; distribution matching; Equations; Feature extraction; feature learning; Invariants; Joints; Kernel; Matching; Optimization; Pattern recognition; Principal component analysis; Strategy; Transfer learning; Visual; Visualization
• DOI: 10.1109/CVPR.2014.183
• ISSN: 1063-6919

Visual domain adaptation, which learns an accurate classifier for a new domain using labeled images from an old domain, has shown promising value in computer vision yet still been a challenging problem. Most prior works have explored two learning strategies independently for domain adaptation: feature matching and instance reweighting. In this paper, we show that both strategies are important and inevitable when the domain difference is substantially large. We therefore put forward a novel Transfer Joint Matching (TJM) approach to model them in a unified optimization problem. Specifically, TJM aims to reduce the domain difference by jointly matching the features and reweighting the instances across domains in a principled dimensionality reduction procedure, and construct new feature representation that is invariant to both the distribution difference and the irrelevant instances. Comprehensive experimental results verify that TJM can significantly outperform competitive methods for cross-domain image recognition problems.