Shao-Yuan Lo   羅紹元

I am a Research Scientist at Honda Research Institute USA. My research lies in Machine Learning, Computer Vision, and Trustworthy AI. Specifically, my recent research focuses on Multimodal Large Language Models, Visual Scene Understanding, and Adversarial Machine Learning.

I obtained my Ph.D. in Electrical and Computer Engineering at Johns Hopkins University in 2023, advised by Prof. Vishal M. Patel. Before that, I received my M.S. (Electronics Engineering) and B.S. (EECS Honors Program) degrees from National Chiao Tung University in 2019 and 2017, respectively, advised by Prof. Hsueh-Ming Hang. I also spent wonderful times as an Applied Scientist Intern at Amazon Just Walk Out team in summer 2022 and at Amazon Astro team in summer 2021.

Email  /  CV  /  Google Scholar  /  Github  /  LinkedIn  /  Twitter

Hiring Summer 2024 Research Interns!! I am always open to collaborating with self-motivated graduate students to conduct advanced research in industry. If you are interested in working with me, please drop me an email along with your resume.

News
  • 02/2024:   2 papers accepted to CVPR 2024. Won the Best Student Paper Award at SPIE Medical Imaging 2024!!
  • 01/2024:   Invited talks at Academia Sinica and National Yang Ming Chiao Tung University.
  • 07/2023:   Joined Honda Research Institute USA as a Research Scientist. See you in San Jose, CA!!
  • 03/2023:   Defended my PhD dissertation!!
  • 02/2023:   1 paper accepted to CVPR 2023.
  • 09/2022:   Accepted to the Google CS Research Mentorship Program.
  • 07/2022:   1 paper accepted to IEEE T-PAMI, and 1 paper accepted to IROS 2022.
  • 05/2022:   Joined Amazon (Just Walk Out team) as an Applied Scientist Intern. See you in Seattle, WA!!
  • 01/2022:   Invited talks at Academia Sinica and National Yang Ming Chiao Tung University.
  • 12/2021:   1 paper accepted to IEEE T-IP.
  • 06/2021:   Invited talk at CVPR 2021 Tutorial on Adversarial Machine Learning in Computer Vision.
  • 05/2021:   Joined Amazon (Astro team) as an Applied Scientist Intern. See you in Bellevue, WA!!
  • 12/2019:   Won the Best Paper Award at ACM Multimedia Asia 2019!!
  • 08/2019:   Joined Johns Hopkins University as a PhD student. See you in Baltimore, MD!!
Publications
b3do

Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation
Shao-Yuan Lo,   Poojan Oza,   Sumanth Chennupati,   Alejandro Galindo,   Vishal M. Patel
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023

arXiv / slides / poster / bibtex

b3do

Deep Learning-based Multi-Organ CT Segmentation with Adversarial Data Augmentation
Shaoyan Pan,   Shao-Yuan Lo,   Min Huang,   Chaoqiong Ma,   Jacob Wynne,   Tonghe Wang,   Tian Liu,   Xiaofeng Yang
SPIE Medical Imaging (SPIE MI), 2023

arXiv / bibtex

b3do

Adversarially Robust One-class Novelty Detection
Shao-Yuan Lo,   Poojan Oza,   Vishal M. Patel
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2022

arXiv / bibtex

b3do

Learning Feature Decomposition for Domain Adaptive Monocular Depth Estimation
Shao-Yuan Lo,   Wei Wang,   Jim Thomas,   Jingjing Zheng,   Vishal M. Patel,   Cheng-Hao Kuo
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022

arXiv / blog / bibtex

b3do

Exploring Adversarially Robust Training for Unsupervised Domain Adaptation
Shao-Yuan Lo,   Vishal M. Patel
Asian Conference on Computer Vision (ACCV), 2022

arXiv / slides / bibtex

b3do

Defending Against Multiple and Unforeseen Adversarial Videos
Shao-Yuan Lo,   Vishal M. Patel
IEEE Transactions on Image Processing (T-IP), 2021
[Journal presentation at ICIP 2022]

arXiv / slides / bibtex

b3do

Error Diffusion Halftoning Against Adversarial Examples
Shao-Yuan Lo,   Vishal M. Patel
IEEE International Conference on Image Processing (ICIP), 2021

arXiv / slides / bibtex

b3do

Overcomplete Representations Against Adversarial Videos
Shao-Yuan Lo,   Jeya Maria Jose Valanarasu,   Vishal M. Patel
IEEE International Conference on Image Processing (ICIP), 2021

arXiv / slides / bibtex

b3do

MultAV: Multiplicative Adversarial Videos
Shao-Yuan Lo,   Vishal M. Patel
IEEE International Conference on Advanced Video and Signal-based Surveillance (AVSS), 2021

arXiv / slides / bibtex

b3do

Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation
Shao-Yuan Lo,   Hsueh-Ming Hang,   Sheng-Wei Chan,   Jing-Jhih Lin
ACM International Conference on Multimedia in Asia (ACM MM Asia), 2019
[Best Paper Award]

arXiv / project page / slides / bibtex

b3do

Exploring Semantic Segmentation on the DCT Representation
Shao-Yuan Lo,   Hsueh-Ming Hang
ACM International Conference on Multimedia in Asia (ACM MM Asia), 2019
[Oral]

arXiv / slides / bibtex

b3do

Multi-Class Lane Semantic Segmentation using Efficient Convolutional Networks
Shao-Yuan Lo,   Hsueh-Ming Hang,   Sheng-Wei Chan,   Jing-Jhih Lin
IEEE International Workshop on Multimedia Signal Processing (MMSP), 2019

arXiv / slides / bibtex

b3do

Incorporating Luminance, Depth and Color Information by a Fusion-based Network for Semantic Segmentation
Shang-Wei Hung,   Shao-Yuan Lo,   Hsueh-Ming Hang
IEEE International Conference on Image Processing (ICIP), 2019
[Oral]

arXiv / project page / slides / bibtex

b3do

Efficient Road Lane Marking Detection with Deep Learning
Ping-Rong Chen*,   Shao-Yuan Lo*,   Hsueh-Ming Hang,   Sheng-Wei Chan,   Jing-Jhih Lin
IEEE International Conference on Digital Signal Processing (DSP), 2018

arXiv / slides / bibtex

Dissertations
b3do

Robust Computer Vision Against Adversarial Examples and Domain Shifts
Shao-Yuan Lo
Ph.D. Thesis, Johns Hopkins University, 2023

thesis / bibtex

b3do

Real-Time Semantic Segmentation Networks for Autonomous Driving
Shao-Yuan Lo
Master Thesis, National Chiao Tung University, 2019

thesis / bibtex

Industrial Experience
Awards
  • First-Year Doctoral Fellowship,   Johns Hopkins University (2019)
  • Dean's List,   National Chiao Tung University (2017)
  • Scholarship to Overseas Exchange Program,   National Chiao Tung University (2016)
Invited Talks
Academic Activities
  • Journal Reviewer:   IEEE T-PAMI,   IEEE T-IP,   IEEE RA-L,   IEEE T-CSVT,   IEEE T-SMC,   Pattern Recognition,   Medical Physics
  • Conference Reviewer:   CVPR,   ICCV,   ECCV,   ICLR,   AAAI,   WACV,   ACCV,   ICIP,   AVSS
  • Teaching Assistant:   Deep Learning (EN.520.638), Johns Hopkins University, Spring (2021, 2022, 2023)
Press Coverage
  • 07/19/2013:   I was reported on China Times (中國時報) when I was graduating from senior high school (National Experimental High School at Hsinchu Science Park).

stats counter   unique visitors since Oct 2020


Template from Jon Barron