Sparse fully convolutional network for face labeling Academic Article uri icon

abstract

  • 2018 Elsevier B.V. This paper proposes a sparse fully convolutional network (FCN) for face labeling. FCN has demonstrated strong capabilities in learning representations for semantic segmentation. However, it often suffers from heavy redundancy in parameters and connections. To ease this problem, group Lasso regularization and intra-group Lasso regularization are utilized to sparsify the convolutional layers of the FCN. Based on this framework, parameters that correspond to the same output channel are grouped into one group, and these parameters are simultaneously zeroed out during training. For the parameters in groups that are not zeroed out, intra-group Lasso provides further regularization. The essence of the regularization framework lies in its ability to offer better feature selection and higher sparsity. Moreover, a fully connected conditional random fields (CRF) model is used to refine the output of the sparse FCN. The proposed approach is evaluated on the LFW face dataset with the state-of-the-art performance. Compared with a non-regularized FCN, the sparse FCN reduces the number of parameters by 91.55% while increasing the segmentation performance by 11% relative error reduction.

published proceedings

  • NEUROCOMPUTING

author list (cited authors)

  • Dong, M., Wen, S., Zeng, Z., Yan, Z., & Huang, T.

citation count

  • 55

complete list of authors

  • Dong, Minghui||Wen, Shiping||Zeng, Zhigang||Yan, Zheng||Huang, Tingwen

publication date

  • February 2019