Cuong Manh Hoang

Seoul National University of Science and Technology

Papers

Total Citations

H-Index

About

Cuong Manh Hoang is a researcher advancing the field of computer vision, with a primary focus on unsupervised image segmentation. His most cited work, "Pixel-level clustering network for unsupervised image segmentation" (2023), introduces a novel deep learning framework that learns to partition images into meaningful regions without requiring labeled training data. This contribution addresses a critical bottleneck in computer vision—the high cost and scarcity of pixel-level annotations—by enabling models to discover semantic structures directly from raw visual data. The paper has garnered 28 citations, reflecting its timely relevance and utility in pushing the boundaries of self-supervised learning. Hoang’s approach, which integrates clustering objectives with convolutional neural networks, offers a scalable solution for applications ranging from medical imaging to autonomous driving. By tackling the challenge of segmenting images at the pixel level without human supervision, his work provides a foundation for more autonomous and adaptable vision systems. As unsupervised learning continues to reshape AI, Hoang’s research stands out for its practical impact and methodological innovation.