1 code implementation • 18 Jun 2021 • Qigong Sun, Xiufang Li, Fanhua Shang, Hongying Liu, Kang Yang, Licheng Jiao, Zhouchen Lin
The training of deep neural networks (DNNs) always requires intensive resources for both computation and data storage.
no code implementations • 4 May 2021 • Qigong Sun, Xiufang Li, Yan Ren, Zhongjian Huang, Xu Liu, Licheng Jiao, Fang Liu
When the precision of quantization is adjusted, it is necessary to fine-tune the quantized model or minimize the quantization noise, which brings inconvenience in practical applications.
no code implementations • 9 Mar 2021 • Qigong Sun, Yan Ren, Licheng Jiao, Xiufang Li, Fanhua Shang, Fang Liu
Inspired by the characteristics of images in the frequency domain, we propose a novel multiscale wavelet quantization (MWQ) method.
no code implementations • 4 Mar 2021 • Qigong Sun, Licheng Jiao, Yan Ren, Xiufang Li, Fanhua Shang, Fang Liu
Since model quantization helps to reduce the model size and computation latency, it has been successfully applied in many applications of mobile phones, embedded devices and smart chips.
1 code implementation • 21 Jul 2019 • Dong Wang, Yicheng Liu, Wenwo Tang, Fanhua Shang, Hongying Liu, Qigong Sun, Licheng Jiao
In this paper, we propose a new first-order gradient-based algorithm to train deep neural networks.
no code implementations • 9 Jun 2019 • Xiufang Li, Qigong Sun, Lingling Li, Zhongle Ren, Fang Liu, Licheng Jiao
Exploiting rich spatial and spectral features contributes to improve the classification accuracy of hyperspectral images (HSIs).
no code implementations • 9 Jun 2019 • Qigong Sun, Xiufang Li, Lingling Li, Xu Liu, Fang Liu, Licheng Jiao
However, their interpretation faces some challenges, e. g., deficiency of labeled data, inadequate utilization of data information and so on.
no code implementations • 31 May 2019 • Qigong Sun, Fanhua Shang, Kang Yang, Xiufang Li, Yan Ren, Licheng Jiao
The training of deep neural networks (DNNs) requires intensive resources both for computation and for storage performance.
no code implementations • 8 Oct 2018 • Qigong Sun, Fanhua Shang, Xiufang Li, Kang Yang, Peizhuo Lv, Licheng Jiao
Deep neural networks require extensive computing resources, and can not be efficiently applied to embedded devices such as mobile phones, which seriously limits their applicability.
1 code implementation • 9 Jul 2018 • Xu Liu, Licheng Jiao, Xu Tang, Qigong Sun, Dan Zhang
Based on sparse scattering coding and convolution neural network, the polarimetric convolutional network is proposed to classify PolSAR images by making full use of polarimetric information.