Yuxin Wu

Yuxin Wu

Research Engineer

Facebook AI Research

About Me

I’m a research engineer at Facebook AI Research. Previously, I obtained my Master’s degree in computer vision at Carnegie Mellon University.

I work on research problems in computer vision, deep learning, reinforcement learning. I also enjoy building powerful frameworks and infrastructure for research, such as detectron2 and tensorpack.

Education

  • Master in Computer Vision, 2016

    Carnegie Mellon University

  • Bachelor in Computer Science, 2015

    Tsinghua University

Selected Publications

PointRend: Image Segmentation as Rendering

Alexander Kirillov, Yuxin Wu, Kaiming He, Ross Girshick
Computer Vision and Pattern Recognition (CVPR), 2020 (Oral)
Paper Code Slides Talk

Momentum Contrast for Unsupervised Visual Representation Learning

Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, Ross Girshick
Computer Vision and Pattern Recognition (CVPR), 2020 (Oral)
Best Paper Nomination (top 30)
Paper Code Code Slides

Feature Denoising for Improving Adversarial Robustness

The first ImageNet classifier that survives strong white-box adversarial attacks.
Cihang Xie, Yuxin Wu, Laurens van der Maaten, Alan Yuille, Kaiming He
Computer Vision and Pattern Recognition (CVPR), 2019
Paper Code

Group Normalization

A batch-independent alternative to Batch Normalization.
Yuxin Wu, Kaiming He
European Conference on Computer Vision (ECCV), 2018 (Oral)
Best Paper Honorable Mention (top 3)
Paper Code Poster Slides Talk Extended Journal Version

House3D: A Rich and Realistic 3D Environment

Yi Wu, Yuxin Wu, Georgia Gkioxari, Yuandong Tian
Workshop in International Conference on Learning Representations (ICLR), 2018
Paper Code Media

ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games

RL platform that powers large-scale projects such as OpenGO.
Yuandong Tian, Qucheng Gong, Wenling Shang, Yuxin Wu, Lawrence Zitnick
Neural Information Processing Systems (NeurIPS), 2017 (Oral)
Paper Code Slides Talk

Training Agent for First-Person Shooter Game with Actor-Critic Curriculum Learning

Award-winning solution for training AI to play FPS games.
Yuxin Wu, Yuandong Tian
International Conference on Learning Representations (ICLR), 2017
Paper Code Video Demo

DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients

Comprehensive results on low bitwidth neural network.
Shuchang Zhou, Yuxin Wu, Zekun Ni, Xinyu Zhou, He Wen, Yuheng Zou
Tech Report, 2016
Paper Code

Open Source Projects

More at github.

Detectron2

Research platform & production library for object detection, segmentation, and more. Widely used in research community and dozens of Facebook products & services.
Docs
Detectron2

Tensorpack

A neural net training interface on TensorFlow, with focus on speed + flexibility.
Docs
Tensorpack

Tensorpack R-CNN

Reproduce Faster/Mask/Cascade R-CNN in TensorFlow
Tensorpack R-CNN

Adversarial Attack on Face Recognition

Black-box adversarial attacks on AWS/Azure’s public face recognition APIs, the first successful attack of its kind.
Tutorial (Chinese) Media (Chinese)
Adversarial Attack on Face Recognition

OpenPano

Panorama stitching written from scratch in C++.
Tutorial
OpenPano

wechat-dump

Cracking encrypted wechat message history from Android phones by reverse-engineering.
wechat-dump

Ray Tracing Engine

A toy rendering engine with Monte Carlo path tracing.
Ray Tracing Engine

Work Experience

 
 
 
 
 

Research Engineer

Facebook AI Research

March 2017 – Present Menlo Park
Build systems and perform research in computer vision & reinforcement learning.
 
 
 
 
 

Research Assistant

Oculus Research

January 2016 – April 2016 Pittsburgh
Research about face modeling and GANs towards VR avatars.
 
 
 
 
 

Researcher

Megvii (aka Face++)

October 2014 – August 2015 Beijing
In-house deep learning training framework.
Research & products in computer vision, including OCR, model quantization, etc.
 
 
 
 
 

Software Engineering Intern

Google

April 2014 – July 2014 Beijing
SfM (structure from motion) from videos.

Awards

  • Winner of defense track in Competition on Adversarial Attacks and Defenses (CAAD) 2018.

    We trained an ImageNet classifier with state-of-the-art robustness against adversarial attacks. Competition

  • Winner of CTF in Competition on Adversarial Attacks and Defenses (CAAD) CTF 2018.

    We performed successful adversarial attacks / defenses against other teams during the on-site competition. Competition Media (Chinese)

  • Best Paper Honorable Mention award in ECCV 2018. Announcement

  • Google Open Source Peer Bonus in 2017. Announcement

  • Winner of VizDoom AI Competition in CIG 2016.

    Our Doom bot, “F1”, beat all other competitors in a death match by a large margin. Competition Media Video

  • Champion of Student Cluster Competition in both ISC 2015 and ASC 2015.

    Optimize software and hardware for low-power high-performance computation. Media Media

  • Finalist in SIGMOD Programming Contest in SIGMOD 2014.

    Design and implement a large social network database to support efficient queries. Competition Slides Poster

  • Capture the Flags (CTF, a form of security competition): 11th in SECCON CTF 2014, 8th in Codegate CTF 2015, 5th in DEFCON CTF 2015 as a team member of blue-lotus.