{Home} {Publications and Codes} {Research} {Projects} {Professional Activities} {People}

Machine Vision, Image Recognition and Machine Learning

[Discriminative Kernel Transfer Learning]

Paper:

Lei Zhang*, Jian Yang, and David Zhang, Domain class consistency based transfer learning for image classification across domains, Information Sciences, vol. 418-419, pp. 242-257, 2017. [paper]

Abstract:

Distribution mismatch between the modeling data and the query data is a known domain adaptation issue in machine learning. To this end, in this paper, we propose a l 2,1 -norm based discriminative robust kernel transfer learning (DKTL) method for high-level recog- nition tasks. The key idea is to realize robust domain transfer by simultaneously integrat- ing domain-class-consistency (DCC) metric based discriminative subspace learning, kernel learning in reproduced kernel Hilbert space, and representation learning between source and target domain. The DCC metric includes two properties: domain-consistency used to measure the between-domain distribution discrepancy and class-consistency used to mea- sure the within-domain class separability. The essential objective of the proposed trans- fer learning method is to maximize the DCC metric, which is equivalently to minimize the domain-class-inconsistency (DCIC), such that domain distribution mismatch and class inseparability are well formulated and unified simultaneously. The merits of the proposed method include (1) the robust sparse coding selects a few valuable source data with noises (outliers) removed during knowledge transfer, and (2) the proposed DCC metric can pur- sue more discriminative subspaces of different domains. As a result, the maximum class- separability is also well guaranteed. Extensive experiments on a number of visual datasets demonstrate the superiority of the proposed method over other state-of-the-art domain adaptation and transfer learning methods.

Approach:

Datasets:

Experiments:

References:

[1] L. Zhang, S.K. Jha, T. Liu, G. Pei, Discriminative kernel transfer learning via l 2,1 -norm minimization, in: IJCNN, 2016, pp. 2220–2227 .

[2] L. Zhang, W. Zuo, D. Zhang, LSDT: latent sparse domain transfer learning for visual adaptation, IEEE Trans. Image Process. 25 (3) (2016) 1177–1191 .

[3] M. Shao, D. Kit, Y. Fu, Generalized transfer subspace learning through low-rank constraint, Int. J. Comput. Vis. 109 (2014) 74–93 .

[4] M. Long, H. Zhu, J. Wang, M.I. Jordan, Unsupervised domain adaptation with residual transfer networks, NIPS, 2016 .

[5] I.H. Jhuo, D. Liu, D. Lee, S.F. Chang, Robust visual domain adaptation with low-rank reconstruction, in: CVPR, 2012, pp. 2168–2175.