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 significant 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.
|Title of host publication||IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015|
|Publisher||IEEE Computer Society|
|Number of pages||9|
|Publication status||Published - 2015 Oct 14|
|Event||IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 - Boston, United States|
Duration: 2015 Jun 7 → 2015 Jun 12
|Name||Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition|
|Other||IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015|
|Period||15/6/7 → 15/6/12|
Bibliographical notePublisher Copyright:
© 2015 IEEE.
All Science Journal Classification (ASJC) codes
- Computer Vision and Pattern Recognition