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 Yang You

Yang You

Go Wider Instead of Deeper


Jul 25, 2021
Fuzhao Xue, Ziji Shi, Yuxuan Lou, Yong Liu, Yang You

Figure 1 for Go Wider Instead of Deeper
Figure 2 for Go Wider Instead of Deeper
Figure 3 for Go Wider Instead of Deeper
Figure 4 for Go Wider Instead of Deeper

  Access Paper or Ask Questions

An Efficient Training Approach for Very Large Scale Face Recognition


Jun 04, 2021
Kai Wang, Shuo Wang, Zhipeng Zhou, Xiaobo Wang, Xiaojiang Peng, Baigui Sun, Hao Li, Yang You

Figure 1 for An Efficient Training Approach for Very Large Scale Face Recognition
Figure 2 for An Efficient Training Approach for Very Large Scale Face Recognition
Figure 3 for An Efficient Training Approach for Very Large Scale Face Recognition
Figure 4 for An Efficient Training Approach for Very Large Scale Face Recognition
* This is a very effcient framework for ultra-large-scale classification tasks. Our code is available at https://github.com/tiandunx/FFC. We will keep updating! 
  Access Paper or Ask Questions

Concurrent Adversarial Learning for Large-Batch Training


Jun 01, 2021
Yong Liu, Xiangning Chen, Minhao Cheng, Cho-Jui Hsieh, Yang You

Figure 1 for Concurrent Adversarial Learning for Large-Batch Training
Figure 2 for Concurrent Adversarial Learning for Large-Batch Training
Figure 3 for Concurrent Adversarial Learning for Large-Batch Training
Figure 4 for Concurrent Adversarial Learning for Large-Batch Training

  Access Paper or Ask Questions

2.5-dimensional distributed model training


May 30, 2021
Boxiang Wang, Qifan Xu, Zhengda Bian, Yang You

Figure 1 for 2.5-dimensional distributed model training
Figure 2 for 2.5-dimensional distributed model training
Figure 3 for 2.5-dimensional distributed model training
Figure 4 for 2.5-dimensional distributed model training

  Access Paper or Ask Questions

Maximizing Parallelism in Distributed Training for Huge Neural Networks


May 30, 2021
Zhengda Bian, Qifan Xu, Boxiang Wang, Yang You

Figure 1 for Maximizing Parallelism in Distributed Training for Huge Neural Networks
Figure 2 for Maximizing Parallelism in Distributed Training for Huge Neural Networks
Figure 3 for Maximizing Parallelism in Distributed Training for Huge Neural Networks
Figure 4 for Maximizing Parallelism in Distributed Training for Huge Neural Networks
* Technical Report of NUS HPC-AI Lab (https://ai.comp.nus.edu.sg). The leading two authors have equal contributions 
  Access Paper or Ask Questions

Sequence Parallelism: Making 4D Parallelism Possible


May 26, 2021
Shenggui Li, Fuzhao Xue, Yongbin Li, Yang You

Figure 1 for Sequence Parallelism: Making 4D Parallelism Possible
Figure 2 for Sequence Parallelism: Making 4D Parallelism Possible
Figure 3 for Sequence Parallelism: Making 4D Parallelism Possible
Figure 4 for Sequence Parallelism: Making 4D Parallelism Possible

  Access Paper or Ask Questions

An Efficient 2D Method for Training Super-Large Deep Learning Models


Apr 12, 2021
Qifan Xu, Shenggui Li, Chaoyu Gong, Yang You

Figure 1 for An Efficient 2D Method for Training Super-Large Deep Learning Models
Figure 2 for An Efficient 2D Method for Training Super-Large Deep Learning Models
Figure 3 for An Efficient 2D Method for Training Super-Large Deep Learning Models
Figure 4 for An Efficient 2D Method for Training Super-Large Deep Learning Models
* Mr. Qifan Xu finished this work when he was an intern in Dr. Yang You's group at NUS 
  Access Paper or Ask Questions

Skeleton Merger: an Unsupervised Aligned Keypoint Detector


Mar 19, 2021
Ruoxi Shi, Zhengrong Xue, Yang You, Cewu Lu

Figure 1 for Skeleton Merger: an Unsupervised Aligned Keypoint Detector
Figure 2 for Skeleton Merger: an Unsupervised Aligned Keypoint Detector
Figure 3 for Skeleton Merger: an Unsupervised Aligned Keypoint Detector
Figure 4 for Skeleton Merger: an Unsupervised Aligned Keypoint Detector
* CVPR 2021 
  Access Paper or Ask Questions

PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features


Feb 24, 2021
Yang You, Yujing Lou, Ruoxi Shi, Qi Liu, Yu-Wing Tai, Lizhuang Ma, Weiming Wang, Cewu Lu

Figure 1 for PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features
Figure 2 for PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features
Figure 3 for PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features
Figure 4 for PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features

  Access Paper or Ask Questions

Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes


Nov 24, 2020
Yang You, Zelin Ye, Yujing Lou, Chengkun Li, Yong-Lu Li, Lizhuang Ma, Weiming Wang, Cewu Lu

Figure 1 for Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes
Figure 2 for Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes
Figure 3 for Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes
Figure 4 for Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes

  Access Paper or Ask Questions

UKPGAN: Unsupervised KeyPoint GANeration


Nov 24, 2020
Yang You, Wenhai Liu, Yong-Lu Li, Weiming Wang, Cewu Lu

Figure 1 for UKPGAN: Unsupervised KeyPoint GANeration
Figure 2 for UKPGAN: Unsupervised KeyPoint GANeration
Figure 3 for UKPGAN: Unsupervised KeyPoint GANeration
Figure 4 for UKPGAN: Unsupervised KeyPoint GANeration

  Access Paper or Ask Questions

Training EfficientNets at Supercomputer Scale: 83% ImageNet Top-1 Accuracy in One Hour


Nov 05, 2020
Arissa Wongpanich, Hieu Pham, James Demmel, Mingxing Tan, Quoc Le, Yang You, Sameer Kumar

Figure 1 for Training EfficientNets at Supercomputer Scale: 83% ImageNet Top-1 Accuracy in One Hour
Figure 2 for Training EfficientNets at Supercomputer Scale: 83% ImageNet Top-1 Accuracy in One Hour
Figure 3 for Training EfficientNets at Supercomputer Scale: 83% ImageNet Top-1 Accuracy in One Hour

  Access Paper or Ask Questions

83% ImageNet Accuracy in One Hour


Oct 30, 2020
Arissa Wongpanich, Hieu Pham, James Demmel, Mingxing Tan, Quoc Le, Yang You, Sameer Kumar

Figure 1 for 83% ImageNet Accuracy in One Hour
Figure 2 for 83% ImageNet Accuracy in One Hour
Figure 3 for 83% ImageNet Accuracy in One Hour

  Access Paper or Ask Questions

How much progress have we made in neural network training? A New Evaluation Protocol for Benchmarking Optimizers


Oct 19, 2020
Yuanhao Xiong, Xuanqing Liu, Li-Cheng Lan, Yang You, Si Si, Cho-Jui Hsieh

Figure 1 for How much progress have we made in neural network training? A New Evaluation Protocol for Benchmarking Optimizers
Figure 2 for How much progress have we made in neural network training? A New Evaluation Protocol for Benchmarking Optimizers
Figure 3 for How much progress have we made in neural network training? A New Evaluation Protocol for Benchmarking Optimizers
Figure 4 for How much progress have we made in neural network training? A New Evaluation Protocol for Benchmarking Optimizers

  Access Paper or Ask Questions

The Limit of the Batch Size


Jun 15, 2020
Yang You, Yuhui Wang, Huan Zhang, Zhao Zhang, James Demmel, Cho-Jui Hsieh

Figure 1 for The Limit of the Batch Size
Figure 2 for The Limit of the Batch Size
Figure 3 for The Limit of the Batch Size
Figure 4 for The Limit of the Batch Size

  Access Paper or Ask Questions

Semantic Correspondence via 2D-3D-2D Cycle


Apr 20, 2020
Yang You, Chengkun Li, Yujing Lou, Zhoujun Cheng, Lizhuang Ma, Cewu Lu, Weiming Wang

Figure 1 for Semantic Correspondence via 2D-3D-2D Cycle
Figure 2 for Semantic Correspondence via 2D-3D-2D Cycle
Figure 3 for Semantic Correspondence via 2D-3D-2D Cycle
Figure 4 for Semantic Correspondence via 2D-3D-2D Cycle

  Access Paper or Ask Questions

KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations


Mar 21, 2020
Yang You, Yujing Lou, Chengkun Li, Zhoujun Cheng, Liangwei Li, Lizhuang Ma, Cewu Lu, Weiming Wang

Figure 1 for KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations
Figure 2 for KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations
Figure 3 for KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations
Figure 4 for KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations
* 8 pages; to appear in CVPR 2020 
  Access Paper or Ask Questions

Fine-grained Object Semantic Understanding from Correspondences


Dec 29, 2019
Yang You, Chengkun Li, Yujing Lou, Zhoujun Cheng, Liangwei Li, Lizhuang Ma, Weiming Wang, Cewu Lu

Figure 1 for Fine-grained Object Semantic Understanding from Correspondences
Figure 2 for Fine-grained Object Semantic Understanding from Correspondences
Figure 3 for Fine-grained Object Semantic Understanding from Correspondences
Figure 4 for Fine-grained Object Semantic Understanding from Correspondences
* 8 pages 
  Access Paper or Ask Questions

Auto-Precision Scaling for Distributed Deep Learning


Nov 20, 2019
Ruobing Han, Yang You, James Demmel

Figure 1 for Auto-Precision Scaling for Distributed Deep Learning
Figure 2 for Auto-Precision Scaling for Distributed Deep Learning
Figure 3 for Auto-Precision Scaling for Distributed Deep Learning
Figure 4 for Auto-Precision Scaling for Distributed Deep Learning

  Access Paper or Ask Questions

Reducing BERT Pre-Training Time from 3 Days to 76 Minutes


Apr 01, 2019
Yang You, Jing Li, Jonathan Hseu, Xiaodan Song, James Demmel, Cho-Jui Hsieh

Figure 1 for Reducing BERT Pre-Training Time from 3 Days to 76 Minutes
Figure 2 for Reducing BERT Pre-Training Time from 3 Days to 76 Minutes
Figure 3 for Reducing BERT Pre-Training Time from 3 Days to 76 Minutes
Figure 4 for Reducing BERT Pre-Training Time from 3 Days to 76 Minutes

  Access Paper or Ask Questions

Combinational Q-Learning for Dou Di Zhu


Jan 24, 2019
Yang You, Liangwei Li, Baisong Guo, Weiming Wang, Cewu Lu

Figure 1 for Combinational Q-Learning for Dou Di Zhu
Figure 2 for Combinational Q-Learning for Dou Di Zhu
Figure 3 for Combinational Q-Learning for Dou Di Zhu
Figure 4 for Combinational Q-Learning for Dou Di Zhu
* 8 pages 
  Access Paper or Ask Questions

Large-Batch Training for LSTM and Beyond


Jan 24, 2019
Yang You, Jonathan Hseu, Chris Ying, James Demmel, Kurt Keutzer, Cho-Jui Hsieh

Figure 1 for Large-Batch Training for LSTM and Beyond
Figure 2 for Large-Batch Training for LSTM and Beyond
Figure 3 for Large-Batch Training for LSTM and Beyond
Figure 4 for Large-Batch Training for LSTM and Beyond
* Preprint. Work in progress. We may update this draft recently 
  Access Paper or Ask Questions

PRIN: Pointwise Rotation-Invariant Network


Dec 07, 2018
Yang You, Yujing Lou, Qi Liu, Lizhuang Ma, Weiming Wang, Yuwing Tai, Cewu Lu

Figure 1 for PRIN: Pointwise Rotation-Invariant Network
Figure 2 for PRIN: Pointwise Rotation-Invariant Network
Figure 3 for PRIN: Pointwise Rotation-Invariant Network
Figure 4 for PRIN: Pointwise Rotation-Invariant Network

  Access Paper or Ask Questions

ImageNet Training in Minutes


Jan 31, 2018
Yang You, Zhao Zhang, Cho-Jui Hsieh, James Demmel, Kurt Keutzer

Figure 1 for ImageNet Training in Minutes
Figure 2 for ImageNet Training in Minutes
Figure 3 for ImageNet Training in Minutes
Figure 4 for ImageNet Training in Minutes

  Access Paper or Ask Questions

Large Batch Training of Convolutional Networks


Sep 13, 2017
Yang You, Igor Gitman, Boris Ginsburg

Figure 1 for Large Batch Training of Convolutional Networks
Figure 2 for Large Batch Training of Convolutional Networks
Figure 3 for Large Batch Training of Convolutional Networks
Figure 4 for Large Batch Training of Convolutional Networks

  Access Paper or Ask Questions