97 citations · 240 across the 13 of their papers we have counts for
Showing 2018 · cs.CVShow all
3 papers · 2 filters
cs.CV2018
Deep Hierarchical Machine: a Flexible Divide-and-Conquer Architecture
Shichao Li, Xin Yang, Tim Cheng
We propose Deep Hierarchical Machine (DHM), a model inspired from the divide-and-conquer strategy while emphasizing representation learning ability and flexibility. A stochastic ro…
cs.CV2018★ 8 cited
Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance
Zechun Liu, Wenhan Luo, Baoyuan Wu +3
In this paper, we study 1-bit convolutional neural networks (CNNs), of which both the weights and activations are binary. While efficient, the lacking of representational capabilit…
cs.CV2018★ 23 cited
Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm
Zechun Liu, Baoyuan Wu, Wenhan Luo +3
In this work, we study the 1-bit convolutional neural networks (CNNs), of which both the weights and activations are binary. While being efficient, the classification accuracy of t…