This paper presents a new multisupervised coupled metric learning (MS-CML) method for low-resolution face image matching.\nWhile coupled metric learning has achieved good performance in degraded face recognition, most existing coupled metric\nlearning methods only adopt the category label as supervision, which easily leads to changes in the distribution of samples in the\ncoupled space. And the accuracy of degraded image matching is seriously influenced by these changes. To address this problem, we\npropose an MS-CML method to train the linear and nonlinear metric model, respectively, which can project the different\nresolution face pairs into the same latent feature space, under which the distance of each positive pair is reduced and that of each\nnegative pair is enlarged. In this work, we defined a novel multisupervised objective function, which consists of a main objective\nfunction and an auxiliary objective function. The supervised information of the main objective function is the category label,\nwhich plays a major supervisory role. The supervised information of the auxiliary objective function is the distribution relationship\nof the samples, which plays an auxiliary supervisory role. Under the supervision of category label and distribution\ninformation, the learned model can better deal with the intraclass multimodal problem, and the features obtained in the coupled\nspace are more easily matched correctly. Experimental results on three different face datasets validate the efficacy of the\nproposed method.
Loading....