Dung-Ru Yu

National Yang Ming Chiao Tung University

Papers

1

Total Citations

6

H-Index

1

About

Dung-Ru Yu is a researcher focused on advancing unsupervised and self-adaptive computer vision systems, with a particular emphasis on face recognition. Their key contribution lies in developing methods that enable machines to learn facial recognition without human-labeled data, a critical challenge for real-world applications like smart homes, healthcare, and home robotics. In their notable 2020 work, "Learning Face Recognition Unsupervisedly by Disentanglement and Self-Augmentation," Yu introduced a novel framework that disentangles identity-related features from environmental variations—such as illumination and camera angle—and uses self-augmentation to adapt to temporal changes in appearance. This approach allows a recognition system to continuously improve and self-adapt within a specific environment, reducing the need for manual retraining. While their citation count (6) reflects a growing interest in this emerging area, Yu's work addresses a pressing need for privacy-preserving, autonomous learning in dynamic settings. Their research bridges the gap between theoretical unsupervised learning and practical deployment, offering a pathway toward more intelligent, adaptive systems that can operate reliably in uncontrolled, everyday environments.

Research Focus

Key Achievements

1
H-Index
1
Papers
6
Total Citations
6
Avg Citations/Paper
🏆 Most Cited Paper
Learning Face Recognition Unsupervisedly by Disentanglement and Self-Augmentation
6 citations · 2020
📈 Most Prolific Year: 2020 (1 Papers)
🤝 Key Collaborators: 4
🏛 Institutions: National Yang Ming Chiao Tung University

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago