Showing cs.CVShow all
2 papers · 1 filter
cs.CV2020
Direct Quantization for Training Highly Accurate Low Bit-width Deep Neural Networks
Tuan Hoang, Thanh-Toan Do, Tam V. Nguyen +1
This paper proposes two novel techniques to train deep convolutional neural networks with low bit-width weights and activations. First, to obtain low bit-width weights, most existi…
cs.CV2018
EasyConvPooling: Random Pooling with Easy Convolution for Accelerating Training and Testing
Jianzhong Sheng, Chuanbo Chen, Chenchen Fu +1
Convolution operations dominate the overall execution time of Convolutional Neural Networks (CNNs). This paper proposes an easy yet efficient technique for both Convolutional Neura…