1.8k citations · 1.9k across the 5 of their papers we have counts for
5 papers
Balanced Quantization: An Effective and Efficient Approach to Quantized Neural Networks
Shuchang Zhou, Yuzhi Wang, He Wen +2
Quantized Neural Networks (QNNs), which use low bitwidth numbers for representing parameters and performing computations, have been proposed to reduce the computation complexity, s…
EAST: An Efficient and Accurate Scene Text Detector
Xinyu Zhou, Cong Yao, He Wen +4
Previous approaches for scene text detection have already achieved promising performances across various benchmarks. However, they usually fall short when dealing with challenging…
Training Bit Fully Convolutional Network for Fast Semantic Segmentation
He Wen, Shuchang Zhou, Zhe Liang +4
Fully convolutional neural networks give accurate, per-pixel prediction for input images and have applications like semantic segmentation. However, a typical FCN usually requires l…
Effective Quantization Methods for Recurrent Neural Networks
Qinyao He, He Wen, Shuchang Zhou +4
Reducing bit-widths of weights, activations, and gradients of a Neural Network can shrink its storage size and memory usage, and also allow for faster training and inference by exp…
DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
Shuchang Zhou, Yuxin Wu, Zekun Ni +3
We propose DoReFa-Net, a method to train convolutional neural networks that have low bitwidth weights and activations using low bitwidth parameter gradients. In particular, during…