← Search

Yudian Li

2 accepted papers

2019

SSN: Learning Sparse Switchable Normalization via SparsestMax

CVPR 2019poster

Normalization methods improve both optimization and generalization of ConvNets. To further boost performance, the recently-proposed switchable normalization (SN) provides a new perspective for deep learning: it learns to select different normalizers for different convolution layers of a ConvNet. How…

Cited by 71PDFcodeScholar