activity
20182021
most citedFusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices

40 citations · 46 across the 5 of their papers we have counts for

collaborators

6 papers

cs.PF2021

Pinpointing the Memory Behaviors of DNN Training

Jiansong Li, Xiao Dong, Guangli Li +9

The training of deep neural networks (DNNs) is usually memory-hungry due to the limited device memory capacity of DNN accelerators. Characterizing the memory behaviors of DNN train…

cs.NE202040 cited

Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices

Guangli Li, Xiu Ma, Xueying Wang +3

The increasing computational cost of deep neural network models limits the applicability of intelligent applications on resource-constrained edge devices. While a number of neural…

cs.DC2020

Accelerating Deep Learning Inference with Cross-Layer Data Reuse on GPUs

Xueying Wang, Guangli Li, Xiao Dong +3

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…

cs.CV2020

LANCE: Efficient Low-Precision Quantized Winograd Convolution for Neural Networks Based on Graphics Processing Units

Guangli Li, Lei Liu, Xueying Wang +2

Accelerating deep convolutional neural networks has become an active topic and sparked an interest in academia and industry. In this paper, we propose an efficient low-precision qu…

cs.CV20192 cited

Background subtraction on depth videos with convolutional neural networks

Xueying Wang, Lei Liu, Guangli Li +3

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 fo…

cs.DC20184 cited

Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge

Guangli Li, Lei Liu, Xueying Wang +3

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 t…