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 Saining Xie

Saining Xie

An Empirical Study of Training Self-Supervised Vision Transformers


May 05, 2021
Xinlei Chen, Saining Xie, Kaiming He

Figure 1 for An Empirical Study of Training Self-Supervised Vision Transformers
Figure 2 for An Empirical Study of Training Self-Supervised Vision Transformers
Figure 3 for An Empirical Study of Training Self-Supervised Vision Transformers
Figure 4 for An Empirical Study of Training Self-Supervised Vision Transformers
* Technical report, 10 pages. v2: corrected "Visual Transformer" to "Vision Transformer" 
  Access Paper or Ask Questions

Pri3D: Can 3D Priors Help 2D Representation Learning?


Apr 22, 2021
Ji Hou, Saining Xie, Benjamin Graham, Angela Dai, Matthias Nießner

Figure 1 for Pri3D: Can 3D Priors Help 2D Representation Learning?
Figure 2 for Pri3D: Can 3D Priors Help 2D Representation Learning?
Figure 3 for Pri3D: Can 3D Priors Help 2D Representation Learning?
Figure 4 for Pri3D: Can 3D Priors Help 2D Representation Learning?

  Access Paper or Ask Questions

An Empirical Study of Training Self-Supervised Visual Transformers


Apr 05, 2021
Xinlei Chen, Saining Xie, Kaiming He

Figure 1 for An Empirical Study of Training Self-Supervised Visual Transformers
Figure 2 for An Empirical Study of Training Self-Supervised Visual Transformers
Figure 3 for An Empirical Study of Training Self-Supervised Visual Transformers
Figure 4 for An Empirical Study of Training Self-Supervised Visual Transformers
* Technical report, 10 pages 
  Access Paper or Ask Questions

On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness


Feb 22, 2021
Eric Mintun, Alexander Kirillov, Saining Xie

Figure 1 for On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness
Figure 2 for On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness
Figure 3 for On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness
Figure 4 for On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness
* 8+13 pages, 6+10 figures 
  Access Paper or Ask Questions

Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts


Dec 16, 2020
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie

Figure 1 for Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts
Figure 2 for Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts
Figure 3 for Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts
Figure 4 for Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts
* project page: https://sekunde.github.io/project_efficient/ 
  Access Paper or Ask Questions

PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding


Jul 22, 2020
Saining Xie, Jiatao Gu, Demi Guo, Charles R. Qi, Leonidas J. Guibas, Or Litany

Figure 1 for PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
Figure 2 for PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
Figure 3 for PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
Figure 4 for PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
* ECCV 2020 (Spotlight) 
  Access Paper or Ask Questions

Graph Structure of Neural Networks


Jul 13, 2020
Jiaxuan You, Jure Leskovec, Kaiming He, Saining Xie

Figure 1 for Graph Structure of Neural Networks
Figure 2 for Graph Structure of Neural Networks
Figure 3 for Graph Structure of Neural Networks
Figure 4 for Graph Structure of Neural Networks
* ICML 2020 
  Access Paper or Ask Questions

FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions


Apr 12, 2020
Alvin Wan, Xiaoliang Dai, Peizhao Zhang, Zijian He, Yuandong Tian, Saining Xie, Bichen Wu, Matthew Yu, Tao Xu, Kan Chen, Peter Vajda, Joseph E. Gonzalez

Figure 1 for FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
Figure 2 for FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
Figure 3 for FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
Figure 4 for FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
* 8 pages, 10 figures, accepted to CVPR 2020 
  Access Paper or Ask Questions

Are Labels Necessary for Neural Architecture Search?


Mar 26, 2020
Chenxi Liu, Piotr Dollár, Kaiming He, Ross Girshick, Alan Yuille, Saining Xie

Figure 1 for Are Labels Necessary for Neural Architecture Search?
Figure 2 for Are Labels Necessary for Neural Architecture Search?
Figure 3 for Are Labels Necessary for Neural Architecture Search?
Figure 4 for Are Labels Necessary for Neural Architecture Search?

  Access Paper or Ask Questions

Momentum Contrast for Unsupervised Visual Representation Learning


Nov 14, 2019
Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, Ross Girshick

Figure 1 for Momentum Contrast for Unsupervised Visual Representation Learning
Figure 2 for Momentum Contrast for Unsupervised Visual Representation Learning
Figure 3 for Momentum Contrast for Unsupervised Visual Representation Learning
Figure 4 for Momentum Contrast for Unsupervised Visual Representation Learning
* Technical report 
  Access Paper or Ask Questions

Decoupling Representation and Classifier for Long-Tailed Recognition


Oct 21, 2019
Bingyi Kang, Saining Xie, Marcus Rohrbach, Zhicheng Yan, Albert Gordo, Jiashi Feng, Yannis Kalantidis

Figure 1 for Decoupling Representation and Classifier for Long-Tailed Recognition
Figure 2 for Decoupling Representation and Classifier for Long-Tailed Recognition
Figure 3 for Decoupling Representation and Classifier for Long-Tailed Recognition
Figure 4 for Decoupling Representation and Classifier for Long-Tailed Recognition

  Access Paper or Ask Questions

Sample-Efficient Neural Architecture Search by Learning Action Space


Jun 17, 2019
Linnan Wang, Saining Xie, Teng Li, Rodrigo Fonseca, Yuandong Tian

Figure 1 for Sample-Efficient Neural Architecture Search by Learning Action Space
Figure 2 for Sample-Efficient Neural Architecture Search by Learning Action Space
Figure 3 for Sample-Efficient Neural Architecture Search by Learning Action Space
Figure 4 for Sample-Efficient Neural Architecture Search by Learning Action Space

  Access Paper or Ask Questions

On Network Design Spaces for Visual Recognition


May 30, 2019
Ilija Radosavovic, Justin Johnson, Saining Xie, Wan-Yen Lo, Piotr Dollár

Figure 1 for On Network Design Spaces for Visual Recognition
Figure 2 for On Network Design Spaces for Visual Recognition
Figure 3 for On Network Design Spaces for Visual Recognition
Figure 4 for On Network Design Spaces for Visual Recognition
* tech report 
  Access Paper or Ask Questions

Exploring Randomly Wired Neural Networks for Image Recognition


Apr 08, 2019
Saining Xie, Alexander Kirillov, Ross Girshick, Kaiming He

Figure 1 for Exploring Randomly Wired Neural Networks for Image Recognition
Figure 2 for Exploring Randomly Wired Neural Networks for Image Recognition
Figure 3 for Exploring Randomly Wired Neural Networks for Image Recognition
Figure 4 for Exploring Randomly Wired Neural Networks for Image Recognition
* Technical report 
  Access Paper or Ask Questions

Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification


Jul 27, 2018
Saining Xie, Chen Sun, Jonathan Huang, Zhuowen Tu, Kevin Murphy

Figure 1 for Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
Figure 2 for Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
Figure 3 for Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
Figure 4 for Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
* ECCV 2018 camera ready 
  Access Paper or Ask Questions

Aggregated Residual Transformations for Deep Neural Networks


Apr 11, 2017
Saining Xie, Ross Girshick, Piotr Dollár, Zhuowen Tu, Kaiming He

Figure 1 for Aggregated Residual Transformations for Deep Neural Networks
Figure 2 for Aggregated Residual Transformations for Deep Neural Networks
Figure 3 for Aggregated Residual Transformations for Deep Neural Networks
Figure 4 for Aggregated Residual Transformations for Deep Neural Networks
* Accepted to CVPR 2017. Code and models: https://github.com/facebookresearch/ResNeXt 
  Access Paper or Ask Questions

Top-Down Learning for Structured Labeling with Convolutional Pseudoprior


Jul 26, 2016
Saining Xie, Xun Huang, Zhuowen Tu

Figure 1 for Top-Down Learning for Structured Labeling with Convolutional Pseudoprior
Figure 2 for Top-Down Learning for Structured Labeling with Convolutional Pseudoprior
Figure 3 for Top-Down Learning for Structured Labeling with Convolutional Pseudoprior
Figure 4 for Top-Down Learning for Structured Labeling with Convolutional Pseudoprior
* To appear in ECCV 2016, 16 pages, 6 figures 
  Access Paper or Ask Questions

Holistically-Nested Edge Detection


Oct 04, 2015
Saining Xie, Zhuowen Tu

Figure 1 for Holistically-Nested Edge Detection
Figure 2 for Holistically-Nested Edge Detection
Figure 3 for Holistically-Nested Edge Detection
Figure 4 for Holistically-Nested Edge Detection
* v2 Add appendix A for updated results (ODS=0.790) on BSDS-500 in a new experiment setting. Fix typos and reorganize formulations. Add Table 2 to discuss the role of deep supervision. Add links to publicly available repository for code, models and data 
  Access Paper or Ask Questions

Deeply-Supervised Nets


Sep 25, 2014
Chen-Yu Lee, Saining Xie, Patrick Gallagher, Zhengyou Zhang, Zhuowen Tu

Figure 1 for Deeply-Supervised Nets
Figure 2 for Deeply-Supervised Nets
Figure 3 for Deeply-Supervised Nets
Figure 4 for Deeply-Supervised Nets
* Patent disclosure, UCSD Docket No. SD2014-313, filed on May 22, 2014 
  Access Paper or Ask Questions