Unsupervised feature selection via self-paced learning and low-redundant regularization

no code implementations • 14 Dec 2021 • Weiyi Li, Hongmei Chen, Tianrui Li, Jihong Wan, Binbin Sang

In this study, an unsupervised feature selection is proposed by integrating the framework of self-paced learning and subspace learning.

feature selection

SMOF: Squeezing More Out of Filters Yields Hardware-Friendly CNN Pruning

no code implementations • 21 Oct 2021 • Yanli Liu, Bochen Guan, Qinwen Xu, Weiyi Li, Shuxue Quan

We develop a CNN pruning framework called SMOF, which Squeezes More Out of Filters by reducing both kernel size and the number of filter channels.

Network Pruning