Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Tien-Ju Yang

Partial Variable Training for Efficient On-Device Federated Learning


Oct 11, 2021
Tien-Ju Yang, Dhruv Guliani, Françoise Beaufays, Giovanni Motta


  Access Paper or Ask Questions

Enabling On-Device Training of Speech Recognition Models with Federated Dropout


Oct 07, 2021
Dhruv Guliani, Lillian Zhou, Changwan Ryu, Tien-Ju Yang, Harry Zhang, Yonghui Xiao, Francoise Beaufays, Giovanni Motta

* \c{opyright} 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses 

  Access Paper or Ask Questions

NetAdaptV2: Efficient Neural Architecture Search with Fast Super-Network Training and Architecture Optimization


Mar 31, 2021
Tien-Ju Yang, Yi-Lun Liao, Vivienne Sze

* Accepted by CVPR 2021 

  Access Paper or Ask Questions

Design Considerations for Efficient Deep Neural Networks on Processing-in-Memory Accelerators


Dec 18, 2019
Tien-Ju Yang, Vivienne Sze

* Accepted by IEDM 2019 

  Access Paper or Ask Questions

SegSort: Segmentation by Discriminative Sorting of Segments


Oct 30, 2019
Jyh-Jing Hwang, Stella X. Yu, Jianbo Shi, Maxwell D. Collins, Tien-Ju Yang, Xiao Zhang, Liang-Chieh Chen

* In ICCV 2019. Webpage & Code: https://jyhjinghwang.github.io/projects/segsort.html 

  Access Paper or Ask Questions

DeeperLab: Single-Shot Image Parser


Mar 12, 2019
Tien-Ju Yang, Maxwell D. Collins, Yukun Zhu, Jyh-Jing Hwang, Ting Liu, Xiao Zhang, Vivienne Sze, George Papandreou, Liang-Chieh Chen

* 20 pages. The code of the proposed Parsing Covering metric is available at http://deeperlab.mit.edu 

  Access Paper or Ask Questions

FastDepth: Fast Monocular Depth Estimation on Embedded Systems


Mar 08, 2019
Diana Wofk, Fangchang Ma, Tien-Ju Yang, Sertac Karaman, Vivienne Sze

* Accepted for presentation at ICRA 2019. 8 pages, 6 figures, 7 tables 

  Access Paper or Ask Questions

NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications


Sep 28, 2018
Tien-Ju Yang, Andrew Howard, Bo Chen, Xiao Zhang, Alec Go, Mark Sandler, Vivienne Sze, Hartwig Adam

* Accepted by ECCV 2018 

  Access Paper or Ask Questions

MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks


Apr 17, 2018
Ariel Gordon, Elad Eban, Ofir Nachum, Bo Chen, Hao Wu, Tien-Ju Yang, Edward Choi

* Added reproducibility and stability figures in the appendix, as well minor typos and clarifications to the main text 

  Access Paper or Ask Questions

Efficient Processing of Deep Neural Networks: A Tutorial and Survey


Aug 13, 2017
Vivienne Sze, Yu-Hsin Chen, Tien-Ju Yang, Joel Emer

* Based on tutorial on DNN Hardware at eyeriss.mit.edu/tutorial.html 

  Access Paper or Ask Questions

Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning


Apr 18, 2017
Tien-Ju Yang, Yu-Hsin Chen, Vivienne Sze

* Published as a conference paper at CVPR 2017 

  Access Paper or Ask Questions