Alert button
Picture for Xiaowe Xu

Xiaowe Xu

Alert button

Quantization of Deep Neural Networks for Accurate EdgeComputing

Apr 25, 2021
Wentao Chen, Hailong Qiu, Jian Zhuang, Chutong Zhang, Yu Hu, Qing Lu, Tianchen Wang, Yiyu Shi†, Meiping Huang, Xiaowe Xu

Figure 1 for Quantization of Deep Neural Networks for Accurate EdgeComputing
Figure 2 for Quantization of Deep Neural Networks for Accurate EdgeComputing
Figure 3 for Quantization of Deep Neural Networks for Accurate EdgeComputing
Figure 4 for Quantization of Deep Neural Networks for Accurate EdgeComputing

Deep neural networks (DNNs) have demonstrated their great potential in recent years, exceeding the per-formance of human experts in a wide range of applications. Due to their large sizes, however, compressiontechniques such as weight quantization and pruning are usually applied before they can be accommodated onthe edge. It is generally believed that quantization leads to performance degradation, and plenty of existingworks have explored quantization strategies aiming at minimum accuracy loss. In this paper, we argue thatquantization, which essentially imposes regularization on weight representations, can sometimes help toimprove accuracy. We conduct comprehensive experiments on three widely used applications: fully con-nected network (FCN) for biomedical image segmentation, convolutional neural network (CNN) for imageclassification on ImageNet, and recurrent neural network (RNN) for automatic speech recognition, and experi-mental results show that quantization can improve the accuracy by 1%, 1.95%, 4.23% on the three applicationsrespectively with 3.5x-6.4x memory reduction.

* 11 pages, 3 figures, 10 tables, accepted by the ACM Journal on Emerging Technologies in Computing Systems (JETC) 
Viaarxiv icon

Multi-Cycle-Consistent Adversarial Networks for Edge Denoising of Computed Tomography Images

Apr 25, 2021
Xiaowe Xu, Jiawei Zhang, Jinglan Liu, Yukun Ding, Tianchen Wang, Hailong Qiu, Haiyun Yuan, Jian Zhuang, Wen Xie, Yuhao Dong, Qianjun Jia, Meiping Huang, Yiyu Shi

Figure 1 for Multi-Cycle-Consistent Adversarial Networks for Edge Denoising of Computed Tomography Images
Figure 2 for Multi-Cycle-Consistent Adversarial Networks for Edge Denoising of Computed Tomography Images
Figure 3 for Multi-Cycle-Consistent Adversarial Networks for Edge Denoising of Computed Tomography Images
Figure 4 for Multi-Cycle-Consistent Adversarial Networks for Edge Denoising of Computed Tomography Images

As one of the most commonly ordered imaging tests, computed tomography (CT) scan comes with inevitable radiation exposure that increases the cancer risk to patients. However, CT image quality is directly related to radiation dose, thus it is desirable to obtain high-quality CT images with as little dose as possible. CT image denoising tries to obtain high dose like high-quality CT images (domain X) from low dose low-quality CTimages (domain Y), which can be treated as an image-to-image translation task where the goal is to learn the transform between a source domain X (noisy images) and a target domain Y (clean images). In this paper, we propose a multi-cycle-consistent adversarial network (MCCAN) that builds intermediate domains and enforces both local and global cycle-consistency for edge denoising of CT images. The global cycle-consistency couples all generators together to model the whole denoising process, while the local cycle-consistency imposes effective supervision on the process between adjacent domains. Experiments show that both local and global cycle-consistency are important for the success of MCCAN, which outperformsCCADN in terms of denoising quality with slightly less computation resource consumption.

* 16 pages, 7 figures, 4 tables, accepted by the ACM Journal on Emerging Technologies in Computing Systems (JETC). arXiv admin note: substantial text overlap with arXiv:2002.12130 
Viaarxiv icon