Untitled Document

Back:
Transfer Learning and Its Applications on Social Media

[Introduction] Transfer learning provides techniques for transferring learned knowledge from a source domain to a target domain by finding a mapping between them. In this paper, we discuss a method for projecting both source and target data to a generalized subspace where each target sample can be represented by some combination of source samples. By employing a low-rank constraint during this transfer, the structure of source and target domains are preserved. This approach has three benefits. First, good alignment between the domains is ensured through the use of only relevant data in some subspace of the source domain in reconstructing the data in the target domain. Second, the discriminative power of the source domain is naturally passed on to the target domain. Third, noisy information will be filtered out in the knowledge transfer. Extensive experiments on synthetic data, and important computer vision problems such as face recognition application and visual domain adaptation for object recognition demonstrate the superiority of the proposed approach over the existing, well-established methods. [Related Work] Ming Shao, Carlos Castillo, Zhenghong Gu, and Yun Fu, Low-Rank Transfer Subspace Learning, International Conference on Data Mining (ICDM), pages 1104--1109, 2012. [pdf] [bib] Ming Shao, Dmitry Kit, and Yun Fu, Generalized Transfer Subspace Learning through Low-Rank Constraint, International Journal on Computer Vision (IJCV), vol. 109, no. 1-2, pages 74--93, 2014. [pdf] [bib] Zhengming Ding, Ming Shao, and Yun Fu, Latent Low-Rank Transfer Subspace Learning for Missing Modality Recognition, AAAI Conference on Artificial Intelligence (AAAI), pages 1192--1198, 2014. [pdf] [bib] Zhengming Ding, Ming Shao, and Yun Fu, Missing Modality Transfer Learning via Latent Low-Rank Constraint, IEEE Transactions on Image Processing (TIP), vol. 24, no. 11, pages 4322--4334, 2015. [pdf] [bib] Zhengming Ding, Ming Shao, and Yun Fu, Latent Low-Rank Transfer Subspace Learning for Missing Modality Recognition, AAAI Conference on Artificial Intelligence (AAAI), pages 1192--1198, 2014. [pdf] [bib] Hongfu Liu, Ming Shao, and Yun Fu, Structure-Preserved Multi-Source Domain Adaptation, IEEE International Conference on Data Mining (ICDM), pages 1059–1064, 2016. [pdf] [bib] Ming Shao, Zhengming Ding, Handong Zhao, and Yun Fu, Spectral Bisection Tree Guided Deep Adaptive Exemplar Autoencoder for Unsupervised Domain Adaptation, AAAI Conference on Artificial Intelligence (AAAI), pages 2023–2029, 2016. [pdf] [bib]

Back:

Transfer Learning and Its Applications on Social Media

[Introduction]

Transfer learning provides techniques for transferring learned knowledge from a source domain to a target domain by finding a mapping between them.

In this paper, we discuss a method for projecting both source and target data to a generalized subspace where each target sample can be represented by some combination of source samples. By employing a low-rank constraint during this transfer, the structure of source and target domains are preserved. This approach has three benefits.

First, good alignment between the domains is ensured through the use of only relevant data in some subspace of the source domain in reconstructing the data in the target domain.
Second, the discriminative power of the source domain is naturally passed on to the target domain.
Third, noisy information will be filtered out in the knowledge transfer.

Extensive experiments on synthetic data, and important computer vision problems such as face recognition application and visual domain adaptation for object recognition demonstrate the superiority of the proposed approach over the existing, well-established methods.

[Related Work]

Ming Shao, Carlos Castillo, Zhenghong Gu, and Yun Fu, Low-Rank Transfer Subspace Learning, International Conference on Data Mining (ICDM), pages 1104--1109, 2012. [pdf] [bib]
Ming Shao, Dmitry Kit, and Yun Fu, Generalized Transfer Subspace Learning through Low-Rank Constraint, International Journal on Computer Vision (IJCV), vol. 109, no. 1-2, pages 74--93, 2014. [pdf] [bib]
Zhengming Ding, Ming Shao, and Yun Fu, Latent Low-Rank Transfer Subspace Learning for Missing Modality Recognition, AAAI Conference on Artificial Intelligence (AAAI), pages 1192--1198, 2014. [pdf] [bib]
Zhengming Ding, Ming Shao, and Yun Fu, Missing Modality Transfer Learning via Latent Low-Rank Constraint, IEEE Transactions on Image Processing (TIP), vol. 24, no. 11, pages 4322--4334, 2015. [pdf] [bib]
Zhengming Ding, Ming Shao, and Yun Fu, Latent Low-Rank Transfer Subspace Learning for Missing Modality Recognition, AAAI Conference on Artificial Intelligence (AAAI), pages 1192--1198, 2014. [pdf] [bib]
Hongfu Liu, Ming Shao, and Yun Fu, Structure-Preserved Multi-Source Domain Adaptation, IEEE International Conference on Data Mining (ICDM), pages 1059–1064, 2016. [pdf] [bib]
Ming Shao, Zhengming Ding, Handong Zhao, and Yun Fu, Spectral Bisection Tree Guided Deep Adaptive Exemplar Autoencoder for Unsupervised Domain Adaptation, AAAI Conference on Artificial Intelligence (AAAI), pages 2023–2029, 2016. [pdf] [bib]