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 Wei Wen

Wei Wen

Brain Age Estimation From MRI Using Cascade Networks with Ranking Loss


Jun 06, 2021
Jian Cheng, Ziyang Liu, Hao Guan, Zhenzhou Wu, Haogang Zhu, Jiyang Jiang, Wei Wen, Dacheng Tao, Tao Liu

Figure 1 for Brain Age Estimation From MRI Using Cascade Networks with Ranking Loss
Figure 2 for Brain Age Estimation From MRI Using Cascade Networks with Ranking Loss
Figure 3 for Brain Age Estimation From MRI Using Cascade Networks with Ranking Loss
Figure 4 for Brain Age Estimation From MRI Using Cascade Networks with Ranking Loss
* Accepted by IEEE transactions on Medical Imaging, 13 pages, 6 figures 
  Access Paper or Ask Questions

TRP: Trained Rank Pruning for Efficient Deep Neural Networks


Apr 30, 2020
Yuhui Xu, Yuxi Li, Shuai Zhang, Wei Wen, Botao Wang, Yingyong Qi, Yiran Chen, Weiyao Lin, Hongkai Xiong

Figure 1 for TRP: Trained Rank Pruning for Efficient Deep Neural Networks
Figure 2 for TRP: Trained Rank Pruning for Efficient Deep Neural Networks
Figure 3 for TRP: Trained Rank Pruning for Efficient Deep Neural Networks
Figure 4 for TRP: Trained Rank Pruning for Efficient Deep Neural Networks
* Accepted by IJCAI2020, An extension version of arXiv:1812.02402 
  Access Paper or Ask Questions

Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification


Apr 20, 2020
Huanrui Yang, Minxue Tang, Wei Wen, Feng Yan, Daniel Hu, Ang Li, Hai Li, Yiran Chen

Figure 1 for Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification
Figure 2 for Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification
Figure 3 for Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification
Figure 4 for Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification
* In proceeding of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). To be presented at EDLCV 2020 workshop co-located with CVPR 2020 
  Access Paper or Ask Questions

Neural Predictor for Neural Architecture Search


Dec 02, 2019
Wei Wen, Hanxiao Liu, Hai Li, Yiran Chen, Gabriel Bender, Pieter-Jan Kindermans

Figure 1 for Neural Predictor for Neural Architecture Search
Figure 2 for Neural Predictor for Neural Architecture Search
Figure 3 for Neural Predictor for Neural Architecture Search
Figure 4 for Neural Predictor for Neural Architecture Search

  Access Paper or Ask Questions

Trained Rank Pruning for Efficient Deep Neural Networks


Oct 11, 2019
Yuhui Xu, Yuxi Li, Shuai Zhang, Wei Wen, Botao Wang, Wenrui Dai, Yingyong Qi, Yiran Chen, Weiyao Lin, Hongkai Xiong

Figure 1 for Trained Rank Pruning for Efficient Deep Neural Networks
* NeurIPS-EMC2 2019 Workshop on Energy Efficient Machine Learning and Cognitive Computing. arXiv admin note: substantial text overlap with arXiv:1812.02402 
  Access Paper or Ask Questions

Traned Rank Pruning for Efficient Deep Neural Networks


Oct 09, 2019
Yuhui Xu, Yuxi Li, Shuai Zhang, Wei Wen, Botao Wang, Wenrui Dai, Yingyong Qi, Yiran Chen, Weiyao Lin, Hongkai Xiong

Figure 1 for Traned Rank Pruning for Efficient Deep Neural Networks
* NeurIPS-EMC2 2019 Workshop on Energy Efficient Machine Learning and Cognitive Computing. arXiv admin note: substantial text overlap with arXiv:1812.02402 
  Access Paper or Ask Questions

Conditional Transferring Features: Scaling GANs to Thousands of Classes with 30% Less High-quality Data for Training


Sep 25, 2019
Chunpeng Wu, Wei Wen, Yiran Chen, Hai Li

Figure 1 for Conditional Transferring Features: Scaling GANs to Thousands of Classes with 30% Less High-quality Data for Training
Figure 2 for Conditional Transferring Features: Scaling GANs to Thousands of Classes with 30% Less High-quality Data for Training
Figure 3 for Conditional Transferring Features: Scaling GANs to Thousands of Classes with 30% Less High-quality Data for Training
Figure 4 for Conditional Transferring Features: Scaling GANs to Thousands of Classes with 30% Less High-quality Data for Training

  Access Paper or Ask Questions

DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures


Aug 27, 2019
Huanrui Yang, Wei Wen, Hai Li

Figure 1 for DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures
Figure 2 for DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures
Figure 3 for DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures
Figure 4 for DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures

  Access Paper or Ask Questions

Joint Pruning on Activations and Weights for Efficient Neural Networks


Jun 19, 2019
Qing Yang, Wei Wen, Zuoguan Wang, Hai Li

Figure 1 for Joint Pruning on Activations and Weights for Efficient Neural Networks
Figure 2 for Joint Pruning on Activations and Weights for Efficient Neural Networks
Figure 3 for Joint Pruning on Activations and Weights for Efficient Neural Networks
Figure 4 for Joint Pruning on Activations and Weights for Efficient Neural Networks

  Access Paper or Ask Questions

AutoGrow: Automatic Layer Growing in Deep Convolutional Networks


Jun 07, 2019
Wei Wen, Feng Yan, Hai Li

Figure 1 for AutoGrow: Automatic Layer Growing in Deep Convolutional Networks
Figure 2 for AutoGrow: Automatic Layer Growing in Deep Convolutional Networks
Figure 3 for AutoGrow: Automatic Layer Growing in Deep Convolutional Networks
Figure 4 for AutoGrow: Automatic Layer Growing in Deep Convolutional Networks

  Access Paper or Ask Questions

PruneTrain: Gradual Structured Pruning from Scratch for Faster Neural Network Training


Jan 26, 2019
Sangkug Lym, Esha Choukse, Siavash Zangeneh, Wei Wen, Mattan Erez, Sujay Shanghavi

Figure 1 for PruneTrain: Gradual Structured Pruning from Scratch for Faster Neural Network Training
Figure 2 for PruneTrain: Gradual Structured Pruning from Scratch for Faster Neural Network Training
Figure 3 for PruneTrain: Gradual Structured Pruning from Scratch for Faster Neural Network Training
Figure 4 for PruneTrain: Gradual Structured Pruning from Scratch for Faster Neural Network Training

  Access Paper or Ask Questions

Mini-batch Serialization: CNN Training with Inter-layer Data Reuse


Sep 30, 2018
Sangkug Lym, Armand Behroozi, Wei Wen, Ge Li, Yongkee Kwon, Mattan Erez

Figure 1 for Mini-batch Serialization: CNN Training with Inter-layer Data Reuse
Figure 2 for Mini-batch Serialization: CNN Training with Inter-layer Data Reuse
Figure 3 for Mini-batch Serialization: CNN Training with Inter-layer Data Reuse
Figure 4 for Mini-batch Serialization: CNN Training with Inter-layer Data Reuse
* 10pages 
  Access Paper or Ask Questions

SmoothOut: Smoothing Out Sharp Minima to Improve Generalization in Deep Learning


Sep 01, 2018
Wei Wen, Yandan Wang, Feng Yan, Cong Xu, Chunpeng Wu, Yiran Chen, Hai Li

Figure 1 for SmoothOut: Smoothing Out Sharp Minima to Improve Generalization in Deep Learning
Figure 2 for SmoothOut: Smoothing Out Sharp Minima to Improve Generalization in Deep Learning
Figure 3 for SmoothOut: Smoothing Out Sharp Minima to Improve Generalization in Deep Learning
Figure 4 for SmoothOut: Smoothing Out Sharp Minima to Improve Generalization in Deep Learning

  Access Paper or Ask Questions

Learning Intrinsic Sparse Structures within Long Short-Term Memory


Feb 11, 2018
Wei Wen, Yuxiong He, Samyam Rajbhandari, Minjia Zhang, Wenhan Wang, Fang Liu, Bin Hu, Yiran Chen, Hai Li

Figure 1 for Learning Intrinsic Sparse Structures within Long Short-Term Memory
Figure 2 for Learning Intrinsic Sparse Structures within Long Short-Term Memory
Figure 3 for Learning Intrinsic Sparse Structures within Long Short-Term Memory
Figure 4 for Learning Intrinsic Sparse Structures within Long Short-Term Memory
* Published in ICLR 2018 ( the Sixth International Conference on Learning Representations) 
  Access Paper or Ask Questions

TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning


Dec 29, 2017
Wei Wen, Cong Xu, Feng Yan, Chunpeng Wu, Yandan Wang, Yiran Chen, Hai Li

Figure 1 for TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning
Figure 2 for TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning
Figure 3 for TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning
Figure 4 for TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning
* NIPS 2017 Oral 
  Access Paper or Ask Questions

Faster CNNs with Direct Sparse Convolutions and Guided Pruning


Jul 28, 2017
Jongsoo Park, Sheng Li, Wei Wen, Ping Tak Peter Tang, Hai Li, Yiran Chen, Pradeep Dubey

Figure 1 for Faster CNNs with Direct Sparse Convolutions and Guided Pruning
Figure 2 for Faster CNNs with Direct Sparse Convolutions and Guided Pruning
Figure 3 for Faster CNNs with Direct Sparse Convolutions and Guided Pruning
Figure 4 for Faster CNNs with Direct Sparse Convolutions and Guided Pruning
* 12 pages, 5 figures 
  Access Paper or Ask Questions

Coordinating Filters for Faster Deep Neural Networks


Jul 25, 2017
Wei Wen, Cong Xu, Chunpeng Wu, Yandan Wang, Yiran Chen, Hai Li

Figure 1 for Coordinating Filters for Faster Deep Neural Networks
Figure 2 for Coordinating Filters for Faster Deep Neural Networks
Figure 3 for Coordinating Filters for Faster Deep Neural Networks
Figure 4 for Coordinating Filters for Faster Deep Neural Networks
* ICCV 2017 
  Access Paper or Ask Questions

Group Scissor: Scaling Neuromorphic Computing Design to Large Neural Networks


Jun 17, 2017
Yandan Wang, Wei Wen, Beiye Liu, Donald Chiarulli, Hai Li

Figure 1 for Group Scissor: Scaling Neuromorphic Computing Design to Large Neural Networks
Figure 2 for Group Scissor: Scaling Neuromorphic Computing Design to Large Neural Networks
Figure 3 for Group Scissor: Scaling Neuromorphic Computing Design to Large Neural Networks
Figure 4 for Group Scissor: Scaling Neuromorphic Computing Design to Large Neural Networks
* Accepted in DAC 2017 
  Access Paper or Ask Questions

A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation


Apr 03, 2017
Chunpeng Wu, Wei Wen, Tariq Afzal, Yongmei Zhang, Yiran Chen, Hai Li

Figure 1 for A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation
Figure 2 for A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation
Figure 3 for A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation
Figure 4 for A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation
* 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR'17) 
  Access Paper or Ask Questions

Classification Accuracy Improvement for Neuromorphic Computing Systems with One-level Precision Synapses


Jan 07, 2017
Yandan Wang, Wei Wen, Linghao Song, Hai Li

Figure 1 for Classification Accuracy Improvement for Neuromorphic Computing Systems with One-level Precision Synapses
Figure 2 for Classification Accuracy Improvement for Neuromorphic Computing Systems with One-level Precision Synapses
Figure 3 for Classification Accuracy Improvement for Neuromorphic Computing Systems with One-level Precision Synapses
Figure 4 for Classification Accuracy Improvement for Neuromorphic Computing Systems with One-level Precision Synapses
* Best Paper Award of ASP-DAC 2017 
  Access Paper or Ask Questions

Learning Structured Sparsity in Deep Neural Networks


Oct 18, 2016
Wei Wen, Chunpeng Wu, Yandan Wang, Yiran Chen, Hai Li

Figure 1 for Learning Structured Sparsity in Deep Neural Networks
Figure 2 for Learning Structured Sparsity in Deep Neural Networks
Figure 3 for Learning Structured Sparsity in Deep Neural Networks
Figure 4 for Learning Structured Sparsity in Deep Neural Networks
* Accepted by NIPS 2016 
  Access Paper or Ask Questions

A New Learning Method for Inference Accuracy, Core Occupation, and Performance Co-optimization on TrueNorth Chip


Jul 16, 2016
Wei Wen, Chunpeng Wu, Yandan Wang, Kent Nixon, Qing Wu, Mark Barnell, Hai Li, Yiran Chen

Figure 1 for A New Learning Method for Inference Accuracy, Core Occupation, and Performance Co-optimization on TrueNorth Chip
Figure 2 for A New Learning Method for Inference Accuracy, Core Occupation, and Performance Co-optimization on TrueNorth Chip
Figure 3 for A New Learning Method for Inference Accuracy, Core Occupation, and Performance Co-optimization on TrueNorth Chip
Figure 4 for A New Learning Method for Inference Accuracy, Core Occupation, and Performance Co-optimization on TrueNorth Chip
* 6 pages; 9 figures; DAC 2016 
  Access Paper or Ask Questions