Kuan-lun Tseng
Software Engineer at 谷歌
Taipei, Taiwan
Summary
👤
Senior🎓
Top SchoolKuan-lun Tseng is a software engineer with nine years of expertise in computer vision, machine learning, and deep learning, currently at Google after a multi-year research career at Microsoft focused on face detection, recognition, and anti-spoofing. He has a strong research-to-production track record—publishing CVPR-related work during his NTU research, contributing TensorFlow implementations of SegNet and 3D U-Net for biomedical segmentation, and shipping SDK-ready algorithms for Face API. Comfortable across the stack, he also works with React and React Native and maintains active open-source projects and Kaggle contributions that demonstrate practical model engineering and dataset pipelines. Known for turning academic ideas into deployable systems, he combines rigorous experimentation with pragmatic engineering to solve real-world vision problems from segmentation to anti-spoofing.
9 years of coding experience
9 years of employment as a software developer
Master's degree Electrical and Electronics Engineering, Master's degree Electrical and Electronics Engineering at National Taiwan University
Github Skills (9)
mask-rcnn10
computer-vision10
faster-rcnn10
image-segmentation10
segmentation10
tensorflow10
python10
seq2seq9
machine-learning9
Programming languages (3)
Github contributions (5)
tkuanlun350/Tensorflow-SegNet
Sep 2016 - Oct 2017
Implement slightly different caffe-segnet in tensorflow
Role in this project:
ML Engineer
ML EngineerContributions:37 commits, 5 PRs, 28 pushes in 1 year 1 month
Contributions summary:Kuan-lun implemented a TensorFlow-based SegNet model, adapting a caffe-segnet implementation. Their contributions included defining the model architecture within `model.py`, developing input pipelines for CamVid datasets, and adding a Seq2Seq model implementation. Code changes suggest the user focused on adapting segmentation models within the Tensorflow environment. The user also refined the models to work with the data and integrated a testing function to validate the implemented models.
caffetensorflowsegnet
tkuanlun350/3DUnet-Tensorflow-Brats18
Jul 2018 - Oct 2018
Contributions:16 commits, 13 pushes, 1 branch in 2 months
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.