Parameter-Efficient Transfer Learning under Federated Learning for Automatic Speech Recognition.
CoRR, 2024
Contemplative Mechanism for Speech Recognition: Speech Encoders can Think.
Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024
Heterogeneous Federated Learning Using Knowledge Codistillation.
CoRR, 2023
Online Model Compression for Federated Learning with Large Models.
Proceedings of the IEEE International Conference on Acoustics, 2023
Federated Pruning: Improving Neural Network Efficiency with Federated Learning.
Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022
Partial Variable Training for Efficient on-Device Federated Learning.
Proceedings of the IEEE International Conference on Acoustics, 2022
Enabling On-Device Training of Speech Recognition Models With Federated Dropout.
Proceedings of the IEEE International Conference on Acoustics, 2022
NetAdaptV2: Efficient Neural Architecture Search With Fast Super-Network Training and Architecture Optimization.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021
Efficient Processing of Deep Neural Networks
Synthesis Lectures on Computer Architecture, Morgan & Claypool Publishers, ISBN: 978-3-031-01766-7, 2020
Eyeriss v2: A Flexible Accelerator for Emerging Deep Neural Networks on Mobile Devices.
IEEE J. Emerg. Sel. Topics Circuits Syst., 2019
Design Considerations for Efficient Deep Neural Networks on Processing-in-Memory Accelerators.
CoRR, 2019
DeeperLab: Single-Shot Image Parser.
CoRR, 2019
FastDepth: Fast Monocular Depth Estimation on Embedded Systems.
Proceedings of the International Conference on Robotics and Automation, 2019
SegSort: Segmentation by Discriminative Sorting of Segments.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019
NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications.
CoRR, 2018
NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications.
Proceedings of the Computer Vision - ECCV 2018, 2018
MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018
Efficient Processing of Deep Neural Networks: A Tutorial and Survey.
Proc. IEEE, 2017
MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks.
CoRR, 2017
Designing Energy-Efficient Convolutional Neural Networks Using Energy-Aware Pruning.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017
A method to estimate the energy consumption of deep neural networks.
Proceedings of the 51st Asilomar Conference on Signals, Systems, and Computers, 2017
A 69mW 140-meter/60fps and 60-meter/300fps intelligent vision SoC for versatile automotive applications.
Proceedings of the Symposium on VLSI Circuits, 2012
WarmL1: A warm-start homotopy-based reconstruction algorithm for sparse signals.
Proceedings of the 2012 IEEE International Symposium on Information Theory, 2012
A high speed feature matching architecture for real-time video stabilization.
Proceedings of the 2012 IEEE International Symposium on Circuits and Systems, 2012
Smart display: A mobile self-adaptive projector-camera system.
Proceedings of the 2011 IEEE International Conference on Multimedia and Expo, 2011