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 Kurt Keutzer

What's Hidden in a One-layer Randomly Weighted Transformer?


Sep 08, 2021
Sheng Shen, Zhewei Yao, Douwe Kiela, Kurt Keutzer, Michael W. Mahoney

* EMNLP 2021 (short) 

  Access Paper or Ask Questions

Emotion Recognition from Multiple Modalities: Fundamentals and Methodologies


Aug 18, 2021
Sicheng Zhao, Guoli Jia, Jufeng Yang, Guiguang Ding, Kurt Keutzer

* Accepted by IEEE Signal Processing Magazine (SPM) 

  Access Paper or Ask Questions

How Much Can CLIP Benefit Vision-and-Language Tasks?


Jul 13, 2021
Sheng Shen, Liunian Harold Li, Hao Tan, Mohit Bansal, Anna Rohrbach, Kai-Wei Chang, Zhewei Yao, Kurt Keutzer

* 14 pages 

  Access Paper or Ask Questions

Scene-aware Learning Network for Radar Object Detection


Jul 03, 2021
Zangwei Zheng, Xiangyu Yue, Kurt Keutzer, Alberto Sangiovanni Vincentelli


  Access Paper or Ask Questions

Learned Token Pruning for Transformers


Jul 02, 2021
Sehoon Kim, Sheng Shen, David Thorsley, Amir Gholami, Joseph Hassoun, Kurt Keutzer


  Access Paper or Ask Questions

Affective Image Content Analysis: Two Decades Review and New Perspectives


Jun 30, 2021
Sicheng Zhao, Xingxu Yao, Jufeng Yang, Guoli Jia, Guiguang Ding, Tat-Seng Chua, Björn W. Schuller, Kurt Keutzer

* Accepted by IEEE TPAMI 

  Access Paper or Ask Questions

Invariant Information Bottleneck for Domain Generalization


Jun 14, 2021
Bo Li, Yifei Shen, Yezhen Wang, Wenzhen Zhu, Colorado J. Reed, Jun Zhang, Dongsheng Li, Kurt Keutzer, Han Zhao

* The work is in progress 

  Access Paper or Ask Questions

Image2Point: 3D Point-Cloud Understanding with Pretrained 2D ConvNets


Jun 08, 2021
Chenfeng Xu, Shijia Yang, Bohan Zhai, Bichen Wu, Xiangyu Yue, Wei Zhan, Peter Vajda, Kurt Keutzer, Masayoshi Tomizuka

* The code is avaliable at: \url{https://github.com/chenfengxu714/image2point

  Access Paper or Ask Questions

MLPruning: A Multilevel Structured Pruning Framework for Transformer-based Models


May 30, 2021
Zhewei Yao, Linjian Ma, Sheng Shen, Kurt Keutzer, Michael W. Mahoney

* 20 pages, 4 figures, 9 tables 

  Access Paper or Ask Questions

HAO: Hardware-aware neural Architecture Optimization for Efficient Inference


Apr 26, 2021
Zhen Dong, Yizhao Gao, Qijing Huang, John Wawrzynek, Hayden K. H. So, Kurt Keutzer

* FCCM 2021 

  Access Paper or Ask Questions

Q-ASR: Integer-only Zero-shot Quantization for Efficient Speech Recognition


Mar 31, 2021
Sehoon Kim, Amir Gholami, Zhewei Yao, Anirudda Nrusimha, Bohan Zhai, Tianren Gao, Michael W. Mahoney, Kurt Keutzer


  Access Paper or Ask Questions

Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation


Mar 31, 2021
Xiangyu Yue, Zangwei Zheng, Shanghang Zhang, Yang Gao, Trevor Darrell, Kurt Keutzer, Alberto Sangiovanni Vincentelli

* CVPR 2021 

  Access Paper or Ask Questions

A Survey of Quantization Methods for Efficient Neural Network Inference


Mar 25, 2021
Amir Gholami, Sehoon Kim, Zhen Dong, Zhewei Yao, Michael W. Mahoney, Kurt Keutzer

* Book Chapter: Low-Power Computer Vision: Improving the Efficiency of Artificial Intelligence 

  Access Paper or Ask Questions

Self-Supervised Pretraining Improves Self-Supervised Pretraining


Mar 25, 2021
Colorado J. Reed, Xiangyu Yue, Ani Nrusimha, Sayna Ebrahimi, Vivek Vijaykumar, Richard Mao, Bo Li, Shanghang Zhang, Devin Guillory, Sean Metzger, Kurt Keutzer, Trevor Darrell


  Access Paper or Ask Questions

You Only Group Once: Efficient Point-Cloud Processing with Token Representation and Relation Inference Module


Mar 24, 2021
Chenfeng Xu, Bohan Zhai, Bichen Wu, Tian Li, Wei Zhan, Peter Vajda, Kurt Keutzer, Masayoshi Tomizuka

* The code is available at https://github.com/chenfengxu714/YOGO.git 

  Access Paper or Ask Questions

Region Similarity Representation Learning


Mar 24, 2021
Tete Xiao, Colorado J Reed, Xiaolong Wang, Kurt Keutzer, Trevor Darrell


  Access Paper or Ask Questions

Improving Context-Based Meta-Reinforcement Learning with Self-Supervised Trajectory Contrastive Learning


Mar 10, 2021
Bernie Wang, Simon Xu, Kurt Keutzer, Yang Gao, Bichen Wu


  Access Paper or Ask Questions

I-BERT: Integer-only BERT Quantization


Feb 11, 2021
Sehoon Kim, Amir Gholami, Zhewei Yao, Michael W. Mahoney, Kurt Keutzer


  Access Paper or Ask Questions

Hessian-Aware Pruning and Optimal Neural Implant


Feb 06, 2021
Shixing Yu, Zhewei Yao, Amir Gholami, Zhen Dong, Michael W Mahoney, Kurt Keutzer


  Access Paper or Ask Questions

Reservoir Transformer


Dec 30, 2020
Sheng Shen, Alexei Baevski, Ari S. Morcos, Kurt Keutzer, Michael Auli, Douwe Kiela


  Access Paper or Ask Questions

BeBold: Exploration Beyond the Boundary of Explored Regions


Dec 15, 2020
Tianjun Zhang, Huazhe Xu, Xiaolong Wang, Yi Wu, Kurt Keutzer, Joseph E. Gonzalez, Yuandong Tian


  Access Paper or Ask Questions

Cross-Domain Sentiment Classification with In-Domain Contrastive Learning


Dec 05, 2020
Tian Li, Xiang Chen, Shanghang Zhang, Zhen Dong, Kurt Keutzer

* 10pages, 2 figures, accepted to NeurIPS 2020 Workshop on Self-supervised Learning. arXiv admin note: text overlap with arXiv:2010.16088 

  Access Paper or Ask Questions

Annotation-Efficient Untrimmed Video Action Recognition


Nov 30, 2020
Yixiong Zou, Shanghang Zhang, Guangyao Chen, Yonghong Tian, Kurt Keutzer, José M. F. Moura


  Access Paper or Ask Questions

FBWave: Efficient and Scalable Neural Vocoders for Streaming Text-To-Speech on the Edge


Nov 25, 2020
Bichen Wu, Qing He, Peizhao Zhang, Thilo Koehler, Kurt Keutzer, Peter Vajda


  Access Paper or Ask Questions

Emotional Semantics-Preserved and Feature-Aligned CycleGAN for Visual Emotion Adaptation


Nov 25, 2020
Sicheng Zhao, Xuanbai Chen, Xiangyu Yue, Chuang Lin, Pengfei Xu, Ravi Krishna, Jufeng Yang, Guiguang Ding, Alberto L. Sangiovanni-Vincentelli, Kurt Keutzer


  Access Paper or Ask Questions

HAWQV3: Dyadic Neural Network Quantization


Nov 20, 2020
Zhewei Yao, Zhen Dong, Zhangcheng Zheng, Amir Gholami, Jiali Yu, Eric Tan, Leyuan Wang, Qijing Huang, Yida Wang, Michael W. Mahoney, Kurt Keutzer


  Access Paper or Ask Questions