Jinyu Ma
算法工程师 at 字节跳动
Shanghai, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolJinyu Ma is an algorithm engineer and computer vision specialist with eight years’ experience building deep learning solutions for visual understanding and medical imaging. A Fudan University alumnus (BS and MS in image and intelligent information processing), he has driven semantic segmentation and multimodal vision-language projects at OPPO, Shukun (数坤), and now ByteDance. Jinyu’s work spans practical production models and research-grade methods, with recent focus on large-scale medical image segmentation models that bridge clinical needs and deployable pipelines. Based in Shanghai, he combines academic training with industry delivery, often translating novel model ideas into robust, product-ready systems. Notably, his career shows a pattern of moving from device-level visual intelligence toward healthcare-scale vision models, reflecting both breadth and a growing specialization.
9 years of coding experience
硕士, 图像与智能信息处理, 硕士, 图像与智能信息处理 at 复旦大学
Github Skills (52)
image-classification10
image-recognition10
multimodal10
mobilenet10
self-supervised-learning10
clip10
vision-transformer10
ai10
resnet10
dockerhub10
docker-image9
data-generation9
pytorch9
openmmlab9
deep-learning9
Programming languages (7)
Github contributions (5)
majinyu666/recognize-anything
Jun 2023 - Jul 2023
Code for the Recognize Anything Model and Tag2Text Model
Contributions:27 pushes, 21 branches in 21 days
Miles-Ma/mmclassification
Jun 2021 - Aug 2021
OpenMMLab Image Classification Toolbox and Benchmark
Contributions:10 pushes, 1 branch in 1 month
pytorchdeep-learningtoolboxobject-detectioncomputer-vision
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.