Xiao Dong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Xiao Dong has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Lei Liu
Chinese Academy of Sciences
5 shared publications - Guangli Li
Institute of Computing Technology, CAS
4 shared publications - Peng Zhao
Huawei 2012 Lab, Beijing, China
4 shared publications - Xueying Wang
Beijing University of Posts and Telecommunications
4 shared publications - Jiansong Li
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China
3 shared publications Xiaobing Feng
Institute of Computing Technology State Key Laboratory of Computer Architecture Chinese Academy of Sciences China
3 shared publications
Latest Publications
- 25 March 2021
- Published by Springer Nature in International Journal of Parallel Programming
- Vol. 49 (5) , 628-645
Compiler-assisted Operator Template Library for DNN Accelerators
- 25 March 2021
- Published by Springer Nature in International Journal of Parallel Programming
- Vol. 49 (5) , 628-645
Compiler-assisted Operator Template Library for DNN Accelerators
- Open Access
Accelerating Deep Learning Inference with Cross-Layer Data Reuse on GPUs
Accelerating the deep learning inference is very important for real-time applications. In this paper, we propose a novel method to fuse the layers of convolutional neural networks (CNNs) on Graphics Processing Units (GPUs), which applies data reuse analysis and access optimization in different levels of the memory hierarchy. To achieve the balance between computation and memory access, we explore the fusion opportunities in the CNN computation graph and propose three fusion modes of convolutional neural networks: straight, merge and split. Then, an approach for generating efficient fused code is designed, which goes deeper in multi-level memory usage for cross-layer data reuse. The effectiveness of our method is evaluated with the network layers from state-of-the-art CNNs on two different GPU platforms, NVIDIA TITAN Xp and Tesla P4. The experiments show that the average speedup is 2.02x on representative structures of CNNs, and 1.57x on end-to-end inference of SqueezeNet.
Open AccessAccelerating Deep Learning Inference with Cross-Layer Data Reuse on GPUs
Accelerating the deep learning inference is very important for real-time applications. In this paper, we propose a novel method to fuse the layers of convolutional neural networks (CNNs) on Graphics Processing Units (GPUs), which applies data reuse analysis and access optimization in different levels of the memory hierarchy. To achieve the balance between computation and memory access, we explore the fusion opportunities in the CNN computation graph and propose three fusion modes of convolutional neural networks: straight, merge and split. Then, an approach for generating efficient fused code is designed, which goes deeper in multi-level memory usage for cross-layer data reuse. The effectiveness of our method is evaluated with the network layers from state-of-the-art CNNs on two different GPU platforms, NVIDIA TITAN Xp and Tesla P4. The experiments show that the average speedup is 2.02x on representative structures of CNNs, and 1.57x on end-to-end inference of SqueezeNet.
- Open Access
Background subtraction on depth videos with convolutional neural networks
Background subtraction is a significant component of computer vision systems. It is widely used in video surveillance, object tracking, anomaly detection, etc. A new data source for background subtraction appeared as the emergence of low-cost depth sensors like Microsof t Kinect, Asus Xtion PRO, etc. In this paper, we propose a background subtraction approach on depth videos, which is based on convolutional neural networks (CNNs), called BGSNet-D (BackGround Subtraction neural Networks for Depth videos). The method can be used in color unavailable scenarios like poor lighting situations, and can also be applied to combine with existing RGB background subtraction methods. A preprocessing strategy is designed to reduce the influences incurred by noise from depth sensors. The experimental results on the SBM-RGBD dataset show that the proposed method outperforms existing methods on depth data.
Open AccessBackground subtraction on depth videos with convolutional neural networks
Background subtraction is a significant component of computer vision systems. It is widely used in video surveillance, object tracking, anomaly detection, etc. A new data source for background subtraction appeared as the emergence of low-cost depth sensors like Microsof t Kinect, Asus Xtion PRO, etc. In this paper, we propose a background subtraction approach on depth videos, which is based on convolutional neural networks (CNNs), called BGSNet-D (BackGround Subtraction neural Networks for Depth videos). The method can be used in color unavailable scenarios like poor lighting situations, and can also be applied to combine with existing RGB background subtraction methods. A preprocessing strategy is designed to reduce the influences incurred by noise from depth sensors. The experimental results on the SBM-RGBD dataset show that the proposed method outperforms existing methods on depth data.
- Open Access
Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge
Recently, deep neural networks (DNNs) have been widely applied in mobile intelligent applications. The inference for the DNNs is usually performed in the cloud. However, it leads to a large overhead of transmitting data via wireless network. In this paper, we demonstrate the advantages of the cloud-edge collaborative inference with quantization. By analyzing the characteristics of layers in DNNs, an auto-tuning neural network quantization framework for collaborative inference is proposed. We study the effectiveness of mixed-precision collaborative inference of state-of-the-art DNNs by using ImageNet dataset. The experimental results show that our framework can generate reasonable network partitions and reduce the storage on mobile devices with trivial loss of accuracy.
Open AccessAuto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge
Recently, deep neural networks (DNNs) have been widely applied in mobile intelligent applications. The inference for the DNNs is usually performed in the cloud. However, it leads to a large overhead of transmitting data via wireless network. In this paper, we demonstrate the advantages of the cloud-edge collaborative inference with quantization. By analyzing the characteristics of layers in DNNs, an auto-tuning neural network quantization framework for collaborative inference is proposed. We study the effectiveness of mixed-precision collaborative inference of state-of-the-art DNNs by using ImageNet dataset. The experimental results show that our framework can generate reasonable network partitions and reduce the storage on mobile devices with trivial loss of accuracy.
- 7 December 2018
- Published by Springer Nature in International Journal of Parallel Programming
- Vol. 47 (3) , 520-534
ElasticActor: An Actor System with Automatic Granularity Adjustment
- 7 December 2018
- Published by Springer Nature in International Journal of Parallel Programming
- Vol. 47 (3) , 520-534
ElasticActor: An Actor System with Automatic Granularity Adjustment