About Me

Hello! I am a research scientist at Facebook AI Research (FAIR), Menlo Park. I received my Ph.D. and M.S. degrees from CSE Department at UC San Diego, advised by Zhuowen Tu. During my PhD study, I also interned at NEC Labs, Adobe, Facebook, Google, DeepMind. Prior to that, I obtained my bachelor degree from Shanghai Jiao Tong University. My primary areas of interest in research are deep learning and computer vision. My goal is to develop improved representation learning techniques that aid machines in comprehending and utilizing massive amounts of structured information, as well as to push the boundaries of visual recognition by learning better representations at scale.

I am serving as an Area Chair for ECCV 2020/2022, ICCV 2021, and CVPR 2021/2022.
Internship opportunity
I'm hiring research interns at FAIR for Summer 2022. If you are passionate about using representation learning to solve challenging tasks in computer vision and machine learning, shoot me an email to apply.


(* indicate equal contribution)
A ConvNet for the 2020s
arXiv 2022

SLIP: Self-supervision meets Language-Image Pre-training
arXiv 2021
Masked Feature Prediction for Self-Supervised Visual Pre-Training
arXiv 2021
Benchmarking Detection Transfer Learning with Vision Transformers
arXiv 2021
Masked Autoencoders are Scalable Vision Learners
arXiv 2021
Pri3D: Can 3D Priors Help 2D Representation Learning?
ICCV 2021
An Empirical Study of Training Self-supervised Vision Transformers
ICCV 2021
Xinlei Chen*, Saining Xie*, Kaiming He,
Oral Presentation
On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness
NeurIPS 2021
Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts
CVPR 2021
Oral Presentation
Sample-Efficient Neural Architecture Search by Learning Action Space
TPAMI 2021

Graph Structure of Neural Networks
ICML 2020
PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
ECCV 2020
Spotlight Presentation
Are Labels Necessary for Neural Architecture Search?
ECCV 2020
Spotlight Presentation
Momentum Contrast for Unsupervised Visual Representation Learning
CVPR 2020
Best Paper Nomination (top 30)
Decoupling Representation and Classifier for Long-Tailed Recognition
ICLR 2020

On Network Design Spaces for Visual Recognition
ICCV 2019
Exploring Randomly Wired Neural Networks for Image Recognition
ICCV 2019
Oral Presentation

Deep Representation Learning with Induced Structural Priors
Ph.D. Thesis, UC San Diego 2018
Saining Xie
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
ECCV 2018
Attentional ShapeContextNet for Point Cloud Recognition
CVPR 2018
Saining Xie*, Sainan Liu*, Zeyu Chen, Zhuowen Tu
Aggregated Residual Transformations for Deep Neural Networks
CVPR 2017
Top-down Learning for Structured Labeling with Convolutional Pseudoprior
ECCV 2016
Saining Xie*, Xun Huang*, Zhuowen Tu
Holistically-Nested Edge Detection
ICCV 2015
Saining Xie, Zhuowen Tu
Marr Prize Honorable Mention
Deeply-Supervised Nets
Chen-Yu Lee*, Saining Xie*, Patrick Gallagher*, Zhengyou Zhang, Zhuowen Tu
Oral Presentation at the NeurIPS'14 Deep Learning Workshop
Hyper-class Augmented and Regularized Deep Learning for Fine-grained Image Classification
CVPR 2015