Alert button
Picture for Kurt Keutzer

Kurt Keutzer

Alert button

SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation

Apr 03, 2020
Chenfeng Xu, Bichen Wu, Zining Wang, Wei Zhan, Peter Vajda, Kurt Keutzer, Masayoshi Tomizuka

Figure 1 for SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation
Figure 2 for SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation
Figure 3 for SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation
Figure 4 for SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation
Viaarxiv icon

Rethinking Batch Normalization in Transformers

Mar 17, 2020
Sheng Shen, Zhewei Yao, Amir Gholami, Michael Mahoney, Kurt Keutzer

Figure 1 for Rethinking Batch Normalization in Transformers
Figure 2 for Rethinking Batch Normalization in Transformers
Figure 3 for Rethinking Batch Normalization in Transformers
Figure 4 for Rethinking Batch Normalization in Transformers
Viaarxiv icon

Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers

Feb 26, 2020
Zhuohan Li, Eric Wallace, Sheng Shen, Kevin Lin, Kurt Keutzer, Dan Klein, Joseph E. Gonzalez

Figure 1 for Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers
Figure 2 for Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers
Figure 3 for Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers
Figure 4 for Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers
Viaarxiv icon

Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey

Feb 26, 2020
Sicheng Zhao, Bo Li, Colorado Reed, Pengfei Xu, Kurt Keutzer

Figure 1 for Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey
Figure 2 for Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey
Figure 3 for Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey
Figure 4 for Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey
Viaarxiv icon

MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation

Feb 19, 2020
Sicheng Zhao, Bo Li, Xiangyu Yue, Pengfei Xu, Kurt Keutzer

Figure 1 for MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation
Figure 2 for MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation
Figure 3 for MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation
Figure 4 for MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation
Viaarxiv icon

Algorithm-hardware Co-design for Deformable Convolution

Feb 19, 2020
Qijing Huang, Dequan Wang, Yizhao Gao, Yaohui Cai, Zhen Dong, Bichen Wu, Kurt Keutzer, John Wawrzynek

Figure 1 for Algorithm-hardware Co-design for Deformable Convolution
Figure 2 for Algorithm-hardware Co-design for Deformable Convolution
Viaarxiv icon

An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated Videos

Feb 12, 2020
Sicheng Zhao, Yunsheng Ma, Yang Gu, Jufeng Yang, Tengfei Xing, Pengfei Xu, Runbo Hu, Hua Chai, Kurt Keutzer

Figure 1 for An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated Videos
Figure 2 for An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated Videos
Figure 3 for An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated Videos
Figure 4 for An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated Videos
Viaarxiv icon

PyHessian: Neural Networks Through the Lens of the Hessian

Jan 02, 2020
Zhewei Yao, Amir Gholami, Kurt Keutzer, Michael Mahoney

Figure 1 for PyHessian: Neural Networks Through the Lens of the Hessian
Figure 2 for PyHessian: Neural Networks Through the Lens of the Hessian
Figure 3 for PyHessian: Neural Networks Through the Lens of the Hessian
Figure 4 for PyHessian: Neural Networks Through the Lens of the Hessian
Viaarxiv icon

ZeroQ: A Novel Zero Shot Quantization Framework

Jan 01, 2020
Yaohui Cai, Zhewei Yao, Zhen Dong, Amir Gholami, Michael W. Mahoney, Kurt Keutzer

Figure 1 for ZeroQ: A Novel Zero Shot Quantization Framework
Figure 2 for ZeroQ: A Novel Zero Shot Quantization Framework
Figure 3 for ZeroQ: A Novel Zero Shot Quantization Framework
Figure 4 for ZeroQ: A Novel Zero Shot Quantization Framework
Viaarxiv icon