Min-Yuan Tseng
Papers
1
Total Citations
6
H-Index
1
About
Min-Yuan Tseng is a researcher specializing in computer vision and machine learning, with a particular focus on unsupervised learning for face recognition systems. His work addresses the critical challenge of developing adaptive facial recognition technologies that can autonomously adjust to environmental changes—such as shifting illumination or camera angles—without requiring labeled data. In his most cited paper, "Learning Face Recognition Unsupervisedly by Disentanglement and Self-Augmentation" (2020), Tseng introduced a novel framework that combines feature disentanglement with self-augmentation techniques, enabling models to learn robust representations from unlabeled data. This contribution is especially significant for real-world applications in smart homes, healthcare, and home robotics, where systems must operate reliably in dynamic, uncontrolled settings. While his citation count (6) reflects the early stage of his career, the practical relevance of his work positions him as an emerging voice in the field. Tseng’s research bridges the gap between theoretical unsupervised learning and deployable, self-adapting vision systems—a promising direction for next-generation intelligent environments.
Research Focus
Key Achievements
Top Papers
- 1