Diluted binary neural network

Yuhan Lin, Lingfeng Niu, Yang Xiao, Ruizhi Zhou

Abstract: Highlights•We provide a new insight on the reason of BNNs’ performance degradation.•A novel DBNN model is proposed to handle the accuracy drop of BNNs.•A sparsity-binarization scheme for weight is given to avoid mandatory representation.•A stable binarization strategy for activation is developed with layer normalization.•A customized proximal gradient method is designed to derive diluted binary weights.