Yuxin Wu

Yuxin Wu

I’m interested and experienced in research, libraries and infrastructure for computer vision and deep learning.

My previous works at Facebook AI Research have received Best Paper Honorable Mention in ECCV 2018, Best Paper Nomination in CVPR 2020, and Mark Everingham Prize in ICCV 2021. I also created detectron2, one of the most popular Facebook AI projects.

Education
  • Master in Computer Vision, 2016

    Carnegie Mellon University

  • Bachelor in Computer Science, 2015

    Tsinghua University

Selected Publications

Rethinking "Batch" in BatchNorm
Tech Review, 2021
Momentum Contrast for Unsupervised Visual Representation Learning
Computer Vision and Pattern Recognition (CVPR), 2020 (Oral)
Best Paper Nomination (top 30)
PointRend: Image Segmentation as Rendering
Computer Vision and Pattern Recognition (CVPR), 2020 (Oral)
Feature Denoising for Improving Adversarial Robustness
The first ImageNet classifier that survives strong white-box adversarial attacks.
Computer Vision and Pattern Recognition (CVPR), 2019
Group Normalization
A batch-independent alternative to Batch Normalization.
European Conference on Computer Vision (ECCV), 2018 (Oral)
Best Paper Honorable Mention (top 3)
House3D: A Rich and Realistic 3D Environment
International Conference on Learning Representations (ICLR), 2018
ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games
Platform that powers large-scale RL projects such as OpenGO.
Neural Information Processing Systems (NeurIPS), 2017 (Oral)

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.
Tensorpack
A neural net training interface on TensorFlow, with focus on speed + flexibility.
Adversarial Attack on Face Recognition
Black-box adversarial attacks on AWS/Azure’s public face recognition APIs, the first successful attack of its kind.
OpenPano
Panorama stitching written from scratch in C++.
wechat-dump
Cracking encrypted wechat message history from Android phones by reverse-engineering.

Work Experience

 
 
 
 
 
Research Engineer
March 2017 – December 2021 Menlo Park
Creator and lead of detectron2.
Publish papers in computer vision & reinforcement learning.
Build systems for Facebook AI Research and Reality Labs.
 
 
 
 
 
Research Assistant
January 2016 – April 2016 Pittsburgh
Research about face modeling and GANs towards VR avatars.
 
 
 
 
 
Researcher
October 2014 – August 2015 Beijing
In-house deep learning training framework.
Research & products in computer vision, including OCR, model quantization, etc.
 
 
 
 
 
Software Engineering Intern
April 2014 – July 2014 Beijing
Implement SfM (structure from motion) from videos and integrate it to Google Maps.

Awards

  • Mark Everingham Prize in ICCV 2021 for the detectron2 project.
    Announcement Media

  • Best Paper Nominee in CVPR 2020 for the paper “Momentum Contrast”.

  • 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.

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

    We performed successful adversarial attacks / defenses against other teams during the live competition.

  • Best Paper Honorable Mention award in ECCV 2018 for the paper “Group Normalization”. Announcement

  • Google Open Source Peer Bonus in 2017 for the tensorpack project. Announcement

  • Winner of VizDoom AI Competition in CIG 2016.

    Our Doom bot, “F1”, beat competitors in death matches 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, as team leader of “blxlrsmb”.

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

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