Nonlinear distance function learning using neural network: an iterative framework

作者：Chen, Junying^*; Zeng, Haoyu; Fan, Na

来源：Multimedia Tools and Applications, 2015, 74(3): 671-688.

DOI：10.1007/s11042-014-1944-z

• Metric learning
• Multimodal learning
• Nonlinearity
• Regression models

In this paper, we extend several existing methods that apply distance function learning to regression problems. We discover that these methods may be viewed as approximating a matrix consisting of desired distances among all training samples. Based on this understanding, we propose an iterative framework where outlier samples are corrected by their neighbors via asymptotically increasing the correlation coefficients between the desired distances and the distances of sample labels. Moreover, using this framework, we find that most existing methods iterate only once. As another extension, we adopt a nonlinear distance function and approximate it with neural network. For a fair comparison, we conduct an experiment on age estimation from face images as a regression problem, and the results are comparable to the state of the art.

• 出版日期2015-2
• 单位河北农业大学; 华东师范大学