activity
20202025
most citedSmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation

8 citations · 23 across the 12 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2023

NetDistiller: Empowering Tiny Deep Learning via In-Situ Distillation

Shunyao Zhang, Yonggan Fu, Shang Wu +4

Boosting the task accuracy of tiny neural networks (TNNs) has become a fundamental challenge for enabling the deployments of TNNs on edge devices which are constrained by strict li…

cs.LG2023

NetBooster: Empowering Tiny Deep Learning By Standing on the Shoulders of Deep Giants

Zhongzhi Yu, Yonggan Fu, Jiayi Yuan +2

Tiny deep learning has attracted increasing attention driven by the substantial demand for deploying deep learning on numerous intelligent Internet-of-Things devices. However, it i…

cs.LG2023

Robust Tickets Can Transfer Better: Drawing More Transferable Subnetworks in Transfer Learning

Yonggan Fu, Ye Yuan, Shang Wu +2

Transfer learning leverages feature representations of deep neural networks (DNNs) pretrained on source tasks with rich data to empower effective finetuning on downstream tasks. Ho…

cs.LG2022★ 2 cited

LDP: Learnable Dynamic Precision for Efficient Deep Neural Network Training and Inference

Zhongzhi Yu, Yonggan Fu, Shang Wu +3

Low precision deep neural network (DNN) training is one of the most effective techniques for boosting DNNs' training efficiency, as it trims down the training cost from the finest…

cs.LG2020★ 8 cited

SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation

Yang Zhao, Xiaohan Chen, Yue Wang +6

We present SmartExchange, an algorithm-hardware co-design framework to trade higher-cost memory storage/access for lower-cost computation, for energy-efficient inference of deep ne…

cs.LG2020★ 7 cited

Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference

Jianghao Shen, Yonggan Fu, Yue Wang +3

While increasingly deep networks are still in general desired for achieving state-of-the-art performance, for many specific inputs a simpler network might already suffice. Existing…