no code implementations • 11 Sep 2020 • Kuo-Liang Chung, De-Wei Hsieh
Based on the created training HDAD-pair dataset, we propose a convolutional neural network-based (CNN-based) binarization method to produce high-quality binarized HDAD maps.
no code implementations • 8 Jun 2020 • Kuo-Liang Chung, Yu-Lun Chang, Bo-Wei Tsai
Given a tolerant accuracy loss, without parameters setting, we begin from the last convolutional layer to the first layer; for each considered layer with less or equal pruning rate relative to its previous layer, our ABSHPC-based process is applied to optimally partition all filters to clusters, where each cluster is thus represented by the filter with the median root mean of the hybrid pyramid, leading to maximal removal of redundant filters.