Yao Qin

Research Scientist @ Google Brain

My name is Yao Qin (秦瑶). I am a research scientist at Google Brain, New York, working on improving robustness of machine learning algorithms. My recent work focus on studying adversarial robustness and uncertainty of deep neural networks. I obtained my Ph.D. degree at UC San Diego in Computer Science, advised by Prof. Garrison W. Cottrell. During my PhD, I was very fortunate to intern at Google Brain, Microsoft Research and NEC Labs America.

NEWS!
  • Jan. 2020: I defend my thesis and join Google Brain, New York.
  • Dec. 2019: Our paper about detecting and diagnosing adversarial images is accepted to ICLR 2020.
  • Apr. 2019: Start my internship at Google Brain, Toronto advised by Geoffrey Hinton, Colin Raffel and Nicholas Frosst.
  • Apr. 2019: Our paper on audio adversarial examples has been accepted to ICML 2019.
  • Sep. 2018: I work as a research intern at Google Brain, Mountain View advised by Ian Goodfellow, Colin Raffel and Nicholas Carlini.

Preprints


Improving Uncertainty Estimates through the Relationship with Adversarial Robustness
Yao Qin, Xuezhi Wang, Alex Beutel, Ed H. Chi
[Paper]

Deflecting Adversarial Attacks
Yao Qin, Nicholas Frosst, Colin Raffel, Garrison Cottrell and Geoffrey Hinton
[Paper]

Evaluation Methodology for Attacks Against Confidence Thresholding Models
Ian Goodfellow, Yao Qin, David Berthelot
[Paper]

Publications


Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions
Yao Qin*, Nicholas Frosst*, Sara Sabour, Colin Raffel, Garrison Cottrell and Geoffrey Hinton
International Conference on Learning Representations (ICLR), 2020
[Paper]

Imperceptible, Robust and Targeted Adversarial Examples for Automatic Speech Recognition
Yao Qin, Nicholas Carlini, Ian Goodfellow, Garrison Cottrell, Colin Raffel
International Conference on Machine Learning (ICML), 2019.
[Paper][Project Page][Code]

Autofocus Layer for Semantic Segmentation
Yao Qin, Konstantinos Kamnitsas, Siddharth Ancha, Jay Nanavati, Garrison Cottrell, Antonio Criminisi, Aditya Nori
International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2018.
Oral presentation (4% acceptance rate)
[Paper][Code]

Hierarchical Cellular Automata for Visual Saliency
Yao Qin*, Mengyang Feng*, Huchuan Lu, Garrison Cottrell
International Journal of Computer Vision (IJCV), 2017.
[Paper][Code]

A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction
Yao Qin, Dongjin Song, Haifeng Chen, Wei Cheng, Guofei Jiang, Garrison Cottrell
International Joint Conference on Artificial Intelligence (IJCAI), 2017.
[Paper][Code][Data]

Opinion Evolution in Open Community
Qiuhui Pan, Yao Qin, Yiqun Xu, Mengfei Tong, Mingfeng He
International Journal of Modern Physics C, 2016.
[Paper]

Saliency Detection via Cellular Automata
Yao Qin, Huchuan Lu , Yiqun Xu, He Wang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
[Paper][Code][中文版]


(* indicates equal contributions.)

Research Experience


Apr. 2019 - Nov. 2019
Research intern at Google Brain, Toronto, Canada
Advised by Geoffrey Hinton, Colin Raffel and Nicholas Frosst.

Sep. 2018 - Jan. 2019
Research intern at Google Brain, Mountain View, USA
Advised by Ian Goodfellow, Colin Raffel and Nicholas Carlini.

Jul. 2018 - Sep. 2018
Research intern at Google Brain, Mountain View, USA
Advised by Suharsh Sivakumar and Raghu Krishnamoorthi.

Mar. 2018 - Jun. 2018
Research intern at Microsoft Research, Asia
Advised by advised by Jingdong Wang.

Jun. 2017 - Sep. 2017
Research intern at Microsoft Research, Cambridge, UK
Advised by Antonio Criminisi and Aditya Nori.

Jun. 2016 - Sep. 2016
Research intern at NEC Lab, New Jersey, USA
Advised by Haifeng Chen and Dongjin Song.

Contacts

  • yaoqin@google.com
  • Google Scholar
  • Github
  • LinkedIn
  • Twitter