113 citations · 229 across the 13 of their papers we have counts for
3 papers · 1 filter
Expectation-Maximization Attention Networks for Semantic Segmentation
Xia Li, Zhisheng Zhong, Jianlong Wu +3
Self-attention mechanism has been widely used for various tasks. It is designed to compute the representation of each position by a weighted sum of the features at all positions. T…
ADA-Tucker: Compressing Deep Neural Networks via Adaptive Dimension Adjustment Tucker Decomposition
Zhisheng Zhong, Fangyin Wei, Zhouchen Lin +1
Despite the recent success of deep learning models in numerous applications, their widespread use on mobile devices is seriously impeded by storage and computational requirements.…
Differentiable Linearized ADMM
Xingyu Xie, Jianlong Wu, Zhisheng Zhong +2
Recently, a number of learning-based optimization methods that combine data-driven architectures with the classical optimization algorithms have been proposed and explored, showing…