2 papers
cs.LG2022
CWP: Instance complexity weighted channel-wise soft masks for network pruning
Jiapeng Wang, Ming Ma, Zhenhua Yu
Existing differentiable channel pruning methods often attach scaling factors or masks behind channels to prune filters with less importance, and implicitly assume uniform contribut…
cs.CV2021
a novel attention-based network for fast salient object detection
Bin Zhang, Yang Wu, Xiaojing Zhang +1
In the current salient object detection network, the most popular method is using U-shape structure. However, the massive number of parameters leads to more consumption of computin…