Multi-objective convolutional learning for face labeling

Sifei Liu, Jimei Yang, Chang Huang, Ming-Hsuan Yang
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
This paper formulates face labeling as a conditional random field with unary and pairwise classifiers. We develop a novel multi-objective learning method that optimizes a single unified deep convolutional network with two distinct non-structured loss functions: one encoding the unary label likelihoods and the other encoding the pairwise label dependencies. Moreover, we regularize the network by using a nonparametric prior as new input channels in addition to the RGB image, and show that
more » ... ant performance improvements can be achieved with a much smaller network size. Experiments on both the LFW and Helen datasets demonstrate state-of-the-art results of the proposed algorithm, and accurate labeling results on challenging images can be obtained by the proposed algorithm for real-world applications.
doi:10.1109/cvpr.2015.7298967 dblp:conf/cvpr/LiuYHY15 fatcat:km4zr53bhjawpfq3f7hqvg3sfq