Multi-Objective Convolutional Learning for Face Labeling
- Title
- Multi-Objective Convolutional Learning for Face Labeling
- Author
- Yang, Ming-hsuan
- Keywords
- Labeling; Face; Training; Testing; Hair; Image edge detection; Semantics
- Issue Date
- 2015-06
- Publisher
- IEEE
- Citation
- Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on 2015 June, Page. 3451-3459
- Abstract
- 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.
- URI
- http://ieeexplore.ieee.org/document/7298967/?isnumber=7298593&arnumber=7298967&tag=1http://hdl.handle.net/20.500.11754/25610
- ISBN
- 978-1-4673-6964-0
- ISSN
- 1063-6919
- DOI
- 10.1109/CVPR.2015.7298967
- Appears in Collections:
- COLLEGE OF ENGINEERING[S](공과대학) > COMPUTER SCIENCE AND ENGINEERING(컴퓨터공학부) > Articles
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML