Chenfei Lou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chenfei Lou has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- An Zou
Shanghai Jiao Tong University
1 shared publication - Xiangjie Li
National Clinical Research Center for Cardiovascular Diseases, State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College , 167A Beilishi Road, Xi Cheng District, Beijing 100037
1 shared publication - Yehan Ma
Shanghai Jiao Tong University
1 shared publication Yingtao Shen
Shanghai Jiao Tong University
1 shared publication- Yuchi Chen
School of Chemistry and Environmental Engineering, Wuhan Institute of Technology, Wuhan, China
1 shared publication - Zhengping Zhu
Shanghai Jiao Tong University
1 shared publication
Latest Publications
- Open Access
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (7) , 8657-8665
Predictive Exit: Prediction of Fine-Grained Early Exits for Computation- and Energy-Efficient Inference
By adding exiting layers to the deep learning networks, early exit can terminate the inference earlier with accurate results. However, the passive decision-making of whether to exit or continue the next layer has to go through every pre-placed exiting layer until it exits. In addition, it is hard to adjust the configurations of the computing platforms alongside the inference proceeds. By incorporating a low-cost prediction engine, we propose a Predictive Exit framework for computation- and energy-efficient deep learning applications. Predictive Exit can forecast where the network will exit (i.e., establish the number of remaining layers to finish the inference), which effectively reduces the network computation cost by exiting on time without running every pre-placed exiting layer. Moreover, according to the number of remaining layers, proper computing configurations (i.e., frequency and voltage) are selected to execute the network to further save energy. Extensive experimental results demonstrate that Predictive Exit achieves up to 96.2% computation reduction and 72.9% energy-saving compared with classic deep learning networks; and 12.8% computation reduction and 37.6% energy-saving compared with the early exit under state-of-the-art exiting strategies, given the same inference accuracy and latency.
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (7) , 8657-8665
Open AccessPredictive Exit: Prediction of Fine-Grained Early Exits for Computation- and Energy-Efficient Inference
By adding exiting layers to the deep learning networks, early exit can terminate the inference earlier with accurate results. However, the passive decision-making of whether to exit or continue the next layer has to go through every pre-placed exiting layer until it exits. In addition, it is hard to adjust the configurations of the computing platforms alongside the inference proceeds. By incorporating a low-cost prediction engine, we propose a Predictive Exit framework for computation- and energy-efficient deep learning applications. Predictive Exit can forecast where the network will exit (i.e., establish the number of remaining layers to finish the inference), which effectively reduces the network computation cost by exiting on time without running every pre-placed exiting layer. Moreover, according to the number of remaining layers, proper computing configurations (i.e., frequency and voltage) are selected to execute the network to further save energy. Extensive experimental results demonstrate that Predictive Exit achieves up to 96.2% computation reduction and 72.9% energy-saving compared with classic deep learning networks; and 12.8% computation reduction and 37.6% energy-saving compared with the early exit under state-of-the-art exiting strategies, given the same inference accuracy and latency.