Search Results for author: Zhonghua Lu

Found 2 papers, 1 papers with code

Computing Wasserstein-p Distance Between Images With Linear Cost

1 code implementation CVPR 2022 Yidong Chen, Chen Li, Zhonghua Lu

In this paper, we propose a novel algorithm to compute the Wasserstein-p distance between discrete measures by restricting the optimal transport (OT) problem on a subset.

CNNPruner: Pruning Convolutional Neural Networks with Visual Analytics

no code implementations8 Sep 2020 Guan Li, Junpeng Wang, Han-Wei Shen, Kaixin Chen, Guihua Shan, Zhonghua Lu

It considers the importance of convolutional filters through both instability and sensitivity, and allows users to interactively create pruning plans according to a desired goal on model size or accuracy.

Cannot find the paper you are looking for? You can Submit a new open access paper.