216 citations · 1.4k across the 66 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2020
Shape Adaptor: A Learnable Resizing Module
Shikun Liu, Zhe Lin, Yilin Wang +3
We present a novel resizing module for neural networks: shape adaptor, a drop-in enhancement built on top of traditional resizing layers, such as pooling, bilinear sampling, and st…
cs.LG2018★ 149 cited
Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers
Jianbo Ye, Xin Lu, Zhe Lin +1
Model pruning has become a useful technique that improves the computational efficiency of deep learning, making it possible to deploy solutions in resource-limited scenarios. A wid…
cs.LG2018★ 6 cited
Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks
Jason Kuen, Xiangfei Kong, Zhe Lin +4
It is desirable to train convolutional networks (CNNs) to run more efficiently during inference. In many cases however, the computational budget that the system has for inference c…