238 citations · 393 across the 6 of their papers we have counts for
6 papers
RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization
Chengpeng Chen, Zichao Guo, Haien Zeng +2
Feature reuse has been a key technique in light-weight convolutional neural networks (CNNs) architecture design. Current methods usually utilize a concatenation operator to keep la…
Pixel-Wise Contrastive Distillation
Junqiang Huang, Zichao Guo
We present a simple but effective pixel-level self-supervised distillation framework friendly to dense prediction tasks. Our method, called Pixel-Wise Contrastive Distillation (PCD…
Angle-based Search Space Shrinking for Neural Architecture Search
Yiming Hu, Yuding Liang, Zichao Guo +5
In this work, we present a simple and general search space shrinking method, called Angle-Based search space Shrinking (ABS), for Neural Architecture Search (NAS). Our approach pro…
Dynamic Region-Aware Convolution
Jin Chen, Xijun Wang, Zichao Guo +2
We propose a new convolution called Dynamic Region-Aware Convolution (DRConv), which can automatically assign multiple filters to corresponding spatial regions where features have…
Single Path One-Shot Neural Architecture Search with Uniform Sampling
Zichao Guo, Xiangyu Zhang, Haoyuan Mu +4
We revisit the one-shot Neural Architecture Search (NAS) paradigm and analyze its advantages over existing NAS approaches. Existing one-shot method, however, is hard to train and n…
MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning
Zechun Liu, Haoyuan Mu, Xiangyu Zhang +4
In this paper, we propose a novel meta learning approach for automatic channel pruning of very deep neural networks. We first train a PruningNet, a kind of meta network, which is a…