Blar i NTNU Open på forfatter "Liu, Di"
-
EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI
Kong, Hao; Liu, Di; Huai, Shuo; Luo, Xiangzhong; Subramaniam, Ravi; Makaya, Christian; Lin, Qian; Liu, Weichen (Peer reviewed; Journal article, 2023) -
Efficient FPGA-Based Sparse Matrix-Vector Multiplication With Data Reuse-Aware Compression
Li, Shiqing; Liu, Di; Liu, Weichen LiuDi (Journal article; Peer reviewed, 2023)Sparse matrix–vector multiplication (SpMV) on FPGAs has gained much attention. The performance of SpMV is mainly determined by the number of multiplications between nonzero matrix elements and the corresponding vector ... -
Energy-efficient computation offloading strategy with task priority in cloud assisted multi-access edge computing
He, Zhenli; Xu, Yanan; Liu, Di; Zhou, Wei; Li, Keqin (Peer reviewed; Journal article, 2023)Multi-access edge computing (MEC) provides cloud-like services at the edge of the radio access network close to mobile devices (MDs). This infrastructure can provide low-latency services to MDs and significantly reduce the ... -
Improving robustness of convolutional neural networks using element-wise activation scaling
Zhang, Zhi-Yuan; Ren, Hao; He, Zhenli; Zhou, Wei; Liu, Di (Peer reviewed; Journal article, 2023)Recent works reveal that re-calibrating intermediate activation of adversarial examples can improve the adversarial robustness of CNN models. The state of the arts exploit this feature at the channel level to help CNN ... -
Latency-constrained DNN architecture learning for edge systems using zerorized batch normalization
Huai, Shuo; Liu, Di; Kong, Hao; Liu, Weichen; Subramaniam, Ravi; Makaya, Christian; Lin, Qian (Journal article; Peer reviewed, 2022)Deep learning applications have been widely adopted on edge devices, to mitigate the privacy and latency issues of accessing cloud servers. Deciding the number of neurons during the design of a deep neural network to ... -
MultiGo - Implementing Parallel Execution for Bare-Metal Golang
Frøyland, Hans Erik (Master thesis, 2023)Denne oppgave går ut på å forbedre bare-metal programvare utvikling for RISCV systemer med MultiGo. MultiGo er en modifikasjon av Embeddedgo. MultiGo legger til støtte for parallelt kjørende tråder, noe Embeddedgo mangler. ... -
OCAP: On-device Class-Aware Pruning for personalized edge DNN models
Ma, Ye-Da; Zhao, Zhi-Chao; Liu, Di; He, Zhenli; Zhou, Wei (Journal article; Peer reviewed, 2023)In this paper, we propose a new on-device class-aware pruning method for edge systems, namely OCAP. The motivation behind is that Deep Neural Network (DNN) models are usually trained with a large dataset so that they can ... -
On Hardware-Aware Design and Optimization of Edge Intelligence
Huai, Shuo; Kong, Hao; Luo, Xiangzhong; Liu, Di; Subramaniam, Ravi; Makaya, Christian; Lin, Qian; Liu, Weichen (Journal article; Peer reviewed, 2023)In this article, the authors explore recent efforts in hardware-aware design and optimization for edge intelligence. The article focuses on techniques such as model compression and neural architecture search to enhance ...