期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 28, 期 9, 页码 4659-4670出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2019.2909652
关键词
Face parsing; receptive field; metrics learning; distillation; deep learning
资金
- Natural Science Foundation of China [U1536203, 61572493, 61876177]
- National Key Research and Development Program of China [2016QY01W0200]
- Major Scientific and Technological Project of Hubei Province [2018AAA068]
In this paper, we propose a design scheme for deep learning networks in the face parsing task with promising accuracy and real-time inference speed. By analyzing the differences between the general image parsing task and face parsing task, we first revisit the structure of traditional FCN and make improvements to adapt to the unique properties of the face parsing task. Especially, the concept of Normalized Receptive Field is proposed to give more insights on designing the network. Then, a novel lass function called Statistical Contextual Loss is introduced, which integrates richer contextual information and regularizes features during training. For further model acceleration, we propose a semi-supervised distillation scheme that effectively transfers the learned knowledge to a lighter network. Extensive experiments on LFW and Helen dataset demonstrate the significant superiority of the new design scheme on both efficacy and efficiency.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据