Yang Zou(邹洋)

Applied Scientist

Rekognition, Amazon Website Services

Biography

I am an Applied Scientist of the Rekognition team at Amazon Website Services, working on computer vision and machine learning. I received my PhD degree in Electrical and Computer Engineering from Carnegie Mellon University, supervised by Prof. Vijayakumar Bhagavatula. My research strives to enable visual machines to learn with minimal supervision. [CV/Resume]

Interests

Deep Learning
Computer Vision
Transfer Learning

Education

PhD in Electrical and Computer Engineering, 2015 - 2020

Carnegie Mellon University
M.Sc. in Automation, 2012 - 2015

Chongqing University
B.Sc. in Mathematics, 2007 - 2011

Chongqing University

News

[2020-09-25] Our paper Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection is accepted to NeurIPS 2020!
[2020-07-21] Our paper Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification is accepted to ECCV 2020 as oral presentation! The code is available at DG-Net-PP git repo.
[2019-10-10] Pytorch Code for Confidence regularized self-training is on github!
[2019-07-22] Confidence regularized self-training is accepted to ICCV 2019 as oral presentation, with three Strong Accepts!
[2019-07-22] Two papers are accepted to ICCV 2019, one oral, and one poster!
[2019-02-24] I will work at NVIDIA research as a research intern in this summer!
[2018-10-18] Domain adaptation for semantic segmentation via class-balanced self-training is accepted to ECCV 2018!
[2018-06-22] We win the first and third places in Domain Adaptation of Semantic Segmentation Challenge in CVPR 2018 Workshop on Autonomous Driving (WAD), hosted by Berkeley DeepDrive and Baidu, Inc!
[2018-06-04] I join General Motors R&D as a research intern for 3 months!

Selected Publications

Zeyi Huang*, Yang Zou*, Vijayakumar Bhagavatula, Dong Huang (* indicates equal contribution) (2020). Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection. NeurIPS 2020.

PDF Code

Yang Zou, Xiaodong Yang, Zhiding Yu, Vijayakumar Bhagavatula and Jan Kautz (2020). Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification. ECCV 2020, Oral Presentation (2%).

PDF Code Slides

Yang Zou, Zhiding Yu, Xiaofeng Liu, Vijayakumar Bhagavatula, Jinsong Wang (2019). Confidence Regularized Self-Training. ICCV 2019, Oral Presentation (4.3%).

PDF Code Poster Slides Bibtex

Xiaofeng Liu*, Yang Zou*, Tong Che*, Peng Ding, Ping Jia, Jane You, Vijayakumar Bhagavatula (* indicates equal contribution) (2019). Conservative Wasserstein Training for Pose Estimation. ICCV 2019.

PDF Bibtex

Yang Zou, Zhiding Yu, Vijayakumar Bhagavatula, Jinsong Wang (2018). Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training. ECCV 2018.

PDF Code Poster Slides Bibtex

Zhiding Yu, Weiyang Liu, Yang Zou, Chen Feng, Srikumar Ramalingam, Vijayakumar Bhagavatula, Jan Kautz (2018). Simultaneous Edge Alignment and Learning. ECCV 2018.

PDF Code Project Poster Slides Video Bibtex

Soheil Kolouri, Yang Zou, Gustavo K. Rohde (2016). Sliced Wasserstein Kernels for Probability Distributions. CVPR 2016.

PDF Code Bibtex

Services

Journal/Conference Reviewer: CVPR, ICCV, ECCV, NeuriPS, TIP, AAAI, IJCAI, WACV, …

Personal

May 8, 2019 1 min read

My piano recitals at Kresge Theatre, CMU.

In the spare time, I enjoy classical music by Franz Liszt, Frédéric Chopin, Joe Hisaishi.　You are welcome to see my Recording of Scherzo No.2 (Frédéric Chopin), and Recording of Liebestraum No.3 (Franz Liszt) at Kresge Theatre, College of Fine Arts, CMU.