Xuebin Qin
Senior Principal Researcher at Huawei Canada
Burnaby, British Columbia, Canada
Summary
🤩
Rockstar🎓
Top SchoolXuebin Qin is a Senior Principal Researcher at Huawei Canada with a decade of experience advancing computer vision and deep learning research across academia and industry. He holds a PhD from the University of Alberta and has driven applied research at institutions including MBZUAI, MEDO.ai, and Microsoft, with a focus on object detection, segmentation, and visual tracking. Xuebin contributed to the widely used U^2-Net portrait segmentation code, demonstrating practical expertise in model design, data pipelines, and image compositing for real-world applications. He combines rigorous academic training with hands-on engineering, shipping research that bridges medical imaging, consumer vision, and industrial R&D. Based in Burnaby, BC, he is known for turning state-of-the-art models into production-ready solutions that address both scientific and product needs.
10 years of coding experience
9 years of employment as a software developer
Doctor of Philosophy (PhD) computer science, Doctor of Philosophy (PhD) computer science at University of AlbertaMaster of Science - MS Cartography and Geography Information System, Master of Science - MS Cartography and Geography Information System at Peking University
Github Skills (19)
pytorch10
python10
image-processing10
model-driven10
model-building10
image-segmentation10
deep-learning10
segmentation10
computer-vision10
modeling10
model-driven-development10
preprocess9
preprocessing9
load-data9
opencv9
Programming languages (1)
Github contributions (5)
xuebinqin/U-2-Net
May 2020 - Aug 2022
The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."
Role in this project:
ML Engineer
ML EngineerContributions:4 reviews, 219 commits, 12 PRs in 2 years 4 months
Contributions summary:Xuebin contributed to the development and testing of a U^2-Net model for portrait image segmentation. Their commits involved creating and modifying Python scripts for face detection, image cropping, and model inference, specifically focusing on the `u2net_portrait_demo.py` and `u2net_portrait_test.py` files. The contributions also included updates to the U2NET model architecture and data loading processes, enhancing the model's ability to perform human segmentation tasks within the repository. Furthermore, the user worked on image compositing, allowing the model's outputs to be integrated with source images.
pytorchsalient-object-detectiondeep-learningimage-segmentationimage-background-removal
xuebinqin/BASNet
Mar 2019 - May 2021
Code for CVPR 2019 paper. BASNet: Boundary-Aware Salient Object Detection
Contributions:1 review, 34 commits, 2 PRs in 2 years 1 month
pytorchsalient-object-detectionboundarybasnetdeep-learning
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.